Improved computer-based platforms for implementing weight-based personalized implant planning during total joint arthroplasty and methods of use thereof

Abstract

To provide computer-based platforms for implementing a personalized implant planning and methods of use thereof.SOLUTION: A method includes: obtaining patient-specific data prior to an implantation of at least one implant into a joint of a patient comprising a first bone member and a second bone member; inputting the patient-specific data into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, configured to output weights assigned to patient-specific functional parameters that facilitate a prioritization for each of the patient-specific functional parameters; and utilizing a surgical plan model to obtain a patient-specific intra-operative surgical plan for the implantation of the at least one implant, based at least in part on the plurality of patient-specific data, intra-operative patient-specific data, patient-specific functional parameters, and / or the plurality of weights.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates generally to orthopaedic surgery and, in at least some embodiments, to an exemplary computer-based platform and method of use for implementing weight-based individualized implant planning during total joint replacement surgery. [Background technology]

[0002] The most common total joint replacement procedures in the United States are total knee replacement (approximately 790,000 per year) and total hip replacement (approximately 450,000 per year). While total joint replacement generally has excellent outcomes, it has been reported that at least a significant portion of patients (e.g., up to 20% or more) may be dissatisfied with their clinical results. While this situation may be due to many factors, including patient expectations, it has also been reported that the surgical technique of the surgical staff plays a key role in determining the success of the clinical outcome. Similarly, despite high survival rates for total joint replacement (e.g., over 95% at 10 years), early revisions due to, for example, joint instability or joint stiffness appear to be primarily due to intraoperative technical errors or the inability to properly define personalized cutting parameters during patient-based surgical planning. Therefore, there may be a need in the art for surgical approaches that reduce intraoperative technical errors and personalize the definition of surgical plans. Summary of the Invention

[0003] In some embodiments, the present disclosure provides an exemplary technically improved computer-based method, the method comprising: acquiring a plurality of patient-specific data values ​​prior to implantation of at least one implant into a patient's joint, the patient's joint including a first bone member and a second bone member; inputting the plurality of patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, that outputs a plurality of weights assigned to the plurality of patient-specific functional parameters that facilitate prioritizing the patient-specific functional parameters relative to the plurality of patient-specific functional parameters; and utilizing a surgical planning model based at least in part on the plurality of patient-specific data values, the plurality of patient-specific functional parameters, and the plurality of weights to obtain a patient-specific intraoperative surgical plan for implantation of the at least one implant, the patient-specific intraoperative surgical plan including at least one surgical parameter based on the patient-specific functional parameter prioritization. initiating a surgical procedure for implantation based on the patient-specific intraoperative surgical plan; inputting, during the surgical procedure, the plurality of intraoperative patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implantation machine learning model, or both, to generate a plurality of updated weights for a plurality of patient-specific functional parameters and an updated patient-specific functional parameter prioritization; inputting, during the surgical procedure, the plurality of updated weights, the plurality of intraoperative patient-specific data values, and the updated patient-specific functional parameter prioritization into the surgical planning model to obtain an updated patient-specific intraoperative surgical plan having the at least one updated surgical parameter; and preparing, during the surgical procedure, the first bone member, the second bone member, or both, based on the updated patient-specific intraoperative surgical plan to complete the implantation of the at least one implant.

[0004] Various embodiments of the present disclosure can be further described with reference to the accompanying drawings, in which like structures are referenced by like numerals throughout the several views. The illustrated drawings are not necessarily to scale, emphasis instead generally being placed on illustrating the principles of the present disclosure. Therefore, specific structural and functional details disclosed herein are not to be construed as limiting, but merely as a representative basis to teach those skilled in the art how to variously employ one or more exemplary embodiments. [Brief explanation of the drawings]

[0005] [Figure 1] Figure 1 shows the adoption of kinematic alignment (KA) among surgeons. [Figure 2] FIG. 2 illustrates a joint replacement complication for functional alignment for a total knee arthroplasty (TKA) in accordance with one or more embodiments of the present invention. [Figure 3] FIG. 3 illustrates a schematic diagram of an operating room using an improved computer-based platform for implant planning during total joint arthroplasty, in accordance with one or more embodiments of the present invention. [Figure 4] FIG. 4 is a block diagram of a controller of an improved computer-based platform for implementing weight-based personalized implant planning during total joint arthroplasty in accordance with one or more embodiments of the present invention. [Figure 5A] FIG. 5A illustrates different inputs for a pre-operative surgical profile in accordance with one or more embodiments of the present invention. [Figure 5B] FIG. 5B illustrates a combined surgical flow, both phased and intraoperative, in accordance with one or more embodiments of the present invention. [Figure 6] FIG. 6 is a table showing data for setting up a surgical plan for TKA considering alignment, size, and joint laxity as areas of interest in accordance with one or more embodiments of the present invention. [Figure 7] FIG. 7 shows graphs of three error functions in accordance with one or more embodiments of the present invention. [Figure 8] FIG. 8 illustrates functional parameter (FP) workflows for expert and non-expert surgeons in accordance with one or more embodiments of the present invention. [Figure 9] FIG. 9 shows pseudocode for training a Functional Parameter Optimization Model (FPOM) using batch gradient descent optimization considering three regions of interest: alignment, size, and relaxation, in accordance with one or more embodiments of the present invention. [Figure 10] FIG. 10 is a block diagram illustrating FPOM model training and model evaluation in accordance with one or more embodiments of the present invention. [Figure 11A] 11A-11C are tables illustrating the difference in the number of adjustment clicks required by a surgeon when employing a history algorithm and a laxity-based planning algorithm, in accordance with one or more embodiments of the present invention. [Figure 11B] 11A-11C are tables illustrating the difference in the number of adjustment clicks required by a surgeon when employing a history algorithm and a laxity-based planning algorithm, in accordance with one or more embodiments of the present invention. [Figure 11C] 11A-11C are tables illustrating the difference in the number of adjustment clicks required by a surgeon when employing a history algorithm and a laxity-based planning algorithm, in accordance with one or more embodiments of the present invention. [Figure 12] FIG. 12 illustrates a block diagram of an exemplary computer-based system / platform in accordance with one or more embodiments of the present disclosure. [Figure 13] FIG. 13 illustrates a block diagram of another exemplary computer-based system / platform in accordance with one or more embodiments of the present disclosure. [Figure 14] 14 and 15 are diagrams illustrating implementations of cloud computing architectures / aspects in which the disclosed techniques may specifically operate, in accordance with one or more embodiments of the present disclosure. [Figure 15]14 and 15 are diagrams illustrating implementations of cloud computing architectures / aspects in which the disclosed techniques may specifically operate, in accordance with one or more embodiments of the present disclosure. [Figure 16] FIG. 16 illustrates a flowchart of a method for implementing weight-based personalized implant planning during total joint arthroplasty in accordance with one or more embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0006] While various detailed embodiments of the present disclosure are disclosed herein in connection with the accompanying figures, it should be understood that the disclosed embodiments are merely exemplary. Additionally, the examples given in connection with the various embodiments of the present disclosure are intended to be illustrative and not limiting.

[0007] Throughout this specification, the following terms have the meanings expressly associated therewith, unless the context clearly dictates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment. Furthermore, as used herein, the phrases "in another embodiment" and "in some other embodiments" do not necessarily refer to different embodiments, although they may. Thus, as described below, various embodiments can be readily combined without departing from the scope or spirit of the present disclosure.

[0008] Additionally, the term "based on" is not exclusive and allows for based on additional unrecited factors unless the context clearly dictates otherwise. Additionally, throughout this specification, the meanings of "a," "an," and "the" include plural references. The meaning of "in" includes "in" and "on."

[0009] It is understood that at least one aspect / function of various embodiments described herein may be performed in real time and / or dynamically. As used herein, the term “real time” refers to an event / action that may occur instantaneously or nearly instantaneously in time when another event / action occurs. For example, “real-time processing,” “real-time computation,” and “real-time execution” all relate to performing a computation during the actual time that an associated physical process (e.g., a user interacting with an application on a mobile device) occurs, such that the results of the computation can be used to guide the physical process.

[0010] As used herein, the terms "dynamically" and "automatically," as well as their logical and / or linguistic associations and / or derivations, mean that a particular event / action can be triggered and / or occur without human intervention. In some embodiments, the event and / or action according to the present disclosure can occur in real time and / or based on a predetermined periodicity of at least one of nanoseconds, nanoseconds, milliseconds, milliseconds, seconds, seconds, minutes, minutes, hourly, hourly, daily, daily, weekly, monthly, etc.

[0011] As used herein, the term "runtime" corresponds to any behavior that is dynamically determined during the execution of a software application or at least a portion of a software application.

[0012] Over the past few years, there has been a clear and dynamic evolution of surgical techniques from a systematic workflow based solely on alignment considerations to a personalized workflow where alignment may be de-emphasized as soft tissue considerations may be added and taken into account. As a result, the adoption of such personalized surgical workflows has seen a tremendous increase in recent years. Specifically, Figure 1 shows that surgeons' adoption of kinematic alignment (KA) has increased from 14% in 2021 to 37% in 2022.

[0013] However, despite these clinical advances, algorithms may be used to set up surgical plans and may still be driven by bony and alignment references rather than the expected soft tissue references. As a result of this mismatch between the intent of the algorithm and the expectations from the surgeon during the surgical procedure, those in the art may need to implement numerous modifications to update the plan defined by the algorithm using bony references to an optimal plan preferred by the surgeon that takes advantage of soft tissue considerations.

[0014] Recent personalized workflows tend to be more complex (e.g., 3D instead of the traditional 2D approach, dynamic acquisition across the entire flexion arc instead of the traditional static acquisition at a fixed angle), leading to an increased amount of data to be processed, a longer learning curve, and longer surgical times.

[0015] Figure 1 illustrates the increasing complexity of joint replacement procedures for functional alignment in total knee arthroplasty (TKA). Between the outdated algorithms sometimes used to define surgical plans and the continuing complexity of surgical workflows sometimes used during joint replacement procedures, there may be a need to develop enhanced algorithms that can generate surgical plans based on processing inputs of interest.

[0016] In at least some aspects of at least some embodiments of the present disclosure, the present specification is directed to a system and method for self-generating surgical plans that can be used in joint replacement using a weight-based model. At least one principle for implementing the system and method described in the present disclosure can use at least one aspect of at least one embodiment described in U.S. Patent No. 12,239,384, which is incorporated herein by reference.

[0017] FIG. 3 schematically illustrates an operating room 10 using an improved computer-based platform for implant planning during total joint replacement surgery in accordance with one or more embodiments of the present disclosure. The embodiment illustrated in FIG. 3 refers to a total knee replacement procedure. FIG. 3 shows a surgeon 15 operating on a patient's leg 25 positioned on an operating table 35. The patient's leg 25 can be positioned through a surgical drape opening 27 to allow the surgeon 15 access to the leg 25. In this exemplary embodiment, the surgeon 15 can perform a total knee replacement on the patient through an incision 22 made by the surgeon 15 to expose the patient's knee joint 20. As shown in FIG. 3, the leg 25 can include an upper portion 32 (e.g., first portion—thigh) having a femur 30 (e.g., first bone member), a lower portion 34 (e.g., second portion—calf) having a tibia 45 (e.g., second bone member), and the knee joint 20.

[0018] In some embodiments, at least one first tracking device 40A may be coupled to the upper portion 32 of the leg 25 (e.g., a first bone member) and at least one second tracking device 40B may be coupled to the lower portion 34 of the leg 25 (e.g., a second bone member). In other embodiments, at least one first tracking device 40A and at least one second tracking device 40B may be rigidly attached to the bone members (e.g., to the femur 30 and tibia 45, respectively, in the embodiment of FIG. 3).

[0019] In some embodiments, the operating room 10 may include at least one imaging camera 50, shown schematically in FIG. 3, attached to an imaging camera assembly 51. It should be noted that any suitable number of cameras of any suitable type may be attached to the imaging camera assembly 51, which may be used for tracking 3D objects. The at least one imaging camera 50 may be used to obtain the position and / or orientation of bone members in a three-dimensional (3D) environment.

[0020] In some embodiments, the operating room 10 can include at least one surgical instrument 56A and / or at least one surgical probe 56B placed on a cart 55 that is easily accessible to the surgeon 15 during the total joint replacement procedure.

[0021] In some embodiments, the operating room 10 can include a controller 65 , a keyboard 62 , and a display 60 displaying a graphic user interface (GUI) 61 .

[0022] In this specification, the display 60 that displays the GUI 61 may also be referred to as a surgery support device.

[0023] In some embodiments, the display 60 may be a screen / monitor directly accessible to the surgeon 15 during the surgical procedure and / or a wearable display 17 (e.g., a heads-up display, smart glasses) worn directly by the surgeon 15 during the surgical procedure to provide a computer-controlled augmented reality view to the surgeon 15. The controller 65 may be communicatively coupled to any of the surgical instruments used by the surgeon 15 to perform the total joint replacement.

[0024] In some embodiments, the controller 65 can display on the GUI 61 of the display 60 (e.g., a surgical support device) a surgical plan to assist the surgeon 15 in executing the placement of a joint implant within the joint of a patient undergoing total joint arthroplasty. The keyboard 62 can be used by the surgeon 15 or other medical personnel assisting the surgeon 15 to input patient-specific data into the controller 65 via the keyboard 62 before, during, and / or after the total joint arthroplasty so that algorithms executed by the controller 65 can generate and / or update the surgical plan in real time to assist the surgeon 15 before and / or during the total joint arthroplasty.

[0025] In some embodiments, the controller 65 (e.g., I / O device 92) may receive voice control commands and / or the display device 60 may have touch screen capabilities, instead of using the keyboard 62, where the surgeon 15 can use, for example, a pointer device (e.g., input device 92) to activate graphical user interface elements on the programmed GUI 61 that allow the surgeon 15 to adjust surgical parameters via the display device 60 during the surgical procedure, as described below.

[0026] In some embodiments not shown in FIG. 3, the controller 65 may control a surgical robotic assembly that may be used to robotically perform total joint replacement surgery.

[0027] FIG. 4 is a block diagram of a controller 65 of an improved computer-based platform for implementing weight-based personalized implant planning during total joint arthroplasty in accordance with one or more embodiments of the present disclosure. The controller 65 of the computer-assisted orthopaedic system (CAS) depicted in FIG. 3 may include a processor 70, a memory 80, input / output devices 92, such as a display 60 and a keyboard 62, communications circuitry 90, and surgical instrument and sensor control circuitry 95. The communications circuitry 90 may enable the controller 65 to communicate with other computing devices via any suitable wired and / or wireless communication network. The communications circuitry 90 may enable the controller 65 to communicate with at least one surgical instrument 56A and / or at least one surgical probe 56B, and / or at least one imaging camera 50, and / or at least one first tracking device 40A and / or at least one second tracking device 40B.

[0028] In some embodiments, the surgical instrument and sensor control circuitry 95 may process sensor signals from at least one surgical instrument 56A and at least one surgical probe 56B, and / or at least one imaging camera 50, and / or at least one first tracking device 40A and / or at least one second tracking device 40B, and / or any other suitable surgical devices and / or sensors necessary to perform a total joint replacement procedure. In other embodiments, the surgical instrument and sensor control circuitry 95 may receive commands from the processor 70. The commands may be used to control the at least one surgical instrument 56A and at least one surgical probe 56B during a surgical procedure and / or to control a robotic surgical device performing a surgical total joint replacement procedure in the operating room 10.

[0029] In some embodiments, the processor 70 may execute a surgical plan generator model 75 (also referred to as the surgical planning model 75), which may include an algorithmic software module 77, a trained machine learning model (MLM), or both. The software module 77 may include at least one weight-based implant planning algorithm, as described below. The algorithm may be used to generate and / or update a surgical plan in real time to assist the surgeon 15 before and / or during a total joint arthroplasty procedure. The surgical plan generator model 75 may use an implant profile 71, a surgeon-specific surgical profile 72, and a patient-specific post-operative desired function profile 73 as inputs to the algorithm / MLM software module 77. The surgical plan generator model 75 may use first and second bone member representation modelers 74 and a motion-related data / relaxation curve generation software module 76. The processor executing the surgical plan generator model 75 may output a patient-specific, surgeon-specific (PSSS) surgical plan 78 based at least in part on the weight-based implant planning algorithm. The GUI manager software module 79 may send instructions to the display 60 to display the PSSS surgical plan 78 on the GUI 61 for viewing by the surgeon 15 before and / or during the joint replacement surgical procedure. All or any of the above software routines may be stored in the memory 80.

[0030] In some embodiments, any of the data sets described below can be used to construct a training data set having specific input data vectors and specific output data vectors that can be used to train machine learning model 77. Thus, trained machine learning model 77 may be used to specifically map input data vectors to output data vectors.

[0031] In some embodiments, the memory 80 may store a patient data database 81 that stores data for N patients, where N is an integer. The patient data database 81 may include, for patient 1, a patient record 82 for patient 1, including patient data 83, bone registration / articulation data 84, and a PSSS surgical plan 85. The patient data database 81 may include, for patient N, a patient record 86 for Nth patient N, including patient data 87, bone registration / articulation data 88, and a PSSS surgical plan 89. The memory 80 may store implant kit data in an implant profile database 91 and a post-operative patient outcome database 93. The implant profile database 91 may store multiple implant profiles. The post-operative patient outcome database 93 may store multiple patient outcome data for patients who have undergone multiple joint replacement surgical procedures.

[0032] FIG. 5A illustrates different inputs 250 for a pre-operative surgical profile in accordance with one or more embodiments of the present disclosure. Some of the sets of pre-operative inputs described above may be used independently or in combination, while other sets may be considered optional. Association of these sets of pre-operative inputs may generate a specialized pre-operative surgical profile based on surgeon-specific inputs 255, patient-specific inputs 260, and / or medical practice-specific inputs 265. The set of surgeon-specific inputs may be represented herein as {FP1, FP2, . . .}. The set of patient-specific inputs may be represented herein as {FP I ,FP II The set of medical-specific inputs can be represented herein as {FP a ,FP b This can be expressed as {...}.

[0033] In some embodiments, a pre-operative surgical profile may be stored in memory 80 of controller 65 associated with the CAS technique to be used during the surgical procedure.

[0034] In some embodiments, the surgery may use CAS techniques as shown in operating room 10 (FIG. 3) that uses an improved computer-based platform for implant planning during full-length joint replacement surgery, as well as surgical instruments where at least one surgical instrument 56A may include a tensor, or distractor, to distract soft tissue for laxity acquisition.

[0035] In some embodiments, during surgery, CAS techniques can be used to characterize the joint under consideration as defined by a series of intraoperative inputs including, but not limited to, data related to the size of at least one implant, data related to the angular alignment of at least one implant, and / or data related to the soft tissue in terms of a gap defined as the distance between a first bone and a second bone, or laxity defined as the difference between the gaps (e.g., the difference between the lateral compartment gap and the medial compartment gap).

[0036] FIG. 5B illustrates a surgical flow 270 that combines both pre-operative and intra-operative phases, in accordance with one or more embodiments of the present disclosure. The pre-operative phase may include the processor 70 obtaining a pre-operative surgical profile 275. The intra-operative phase may include the controller 65 of the computerized CAS system 280 receiving the pre-operative surgical profile 275. The computerized CAS system 280 may be controlled using the controller 65. Both the pre-operative surgical profile 275 and the intra-operative inputs 285 may be combined to feed into an algorithm and / or trained machine learning model 77 within the surgical plan generator model 75 of FIG. 4, which may output an updated PSSS surgical plan 78 from the surgical plan generator 75 on a display 290 (e.g., GUI 61 on display 60 of FIG. 1) for display to the surgeon 15, which may include subsequent steps to be performed during the surgical procedure.

[0037] In some embodiments, the parameters and data shown in FIGS. 5A and 5B may be inputs that are input into a surgical plan generator model 75 to generate a patient-specific, surgeon-specific surgical plan 78.

[0038] It should be noted that patient-specific surgeon-specific surgical plan (PSSS) may also be used interchangeably with "patient-specific surgical plan" or "patient-specific intraoperative surgical plan" (e.g., output of surgical planning model 75).

[0039] In some embodiments, the plurality of inputs to the surgical plan generator model 75 may include, but are not limited to, an implant profile for an implant selected from a plurality of implants, a first range of surgeon-specific surgical guidance values ​​for each of a plurality of surgical parameters, at least one functional parameter value for at least one functional parameter representative of the expected functional performance of the joint after implantation, first and second bony member representations, motion-related data for obtaining a relaxation curve, and / or a plurality of weights as described herein below.

[0040] In some embodiments, the personalized surgical plan may utilize at least a patient-based input set as well as a surgeon-based input set, where the patient-based input set may include at least one of the following inputs related to the region of interest: A first set of patient data linked to a first region of interest (e.g., anatomical landmarks sufficient to define joint alignment) A second set of patient data linked to a second region of interest (e.g., anatomical landmarks sufficient to define the dimensional size of the bony members relevant to the joint) A third set of patient data linked to a third region of interest (e.g., soft tissue information alone may be sufficient to define joint laxity), or More generally, "n" sets of patient data linked with "n" regions of interest (many specific regions of interest can be defined depending on the joint being considered)

[0041] In some embodiments, other optional inputs may include, for example: ·Demographics, ·Geographic region, (Expected) activity level, or Degree of joint deformity, This includes, but is not limited to, at least one of:

[0042] In some embodiments, the surgeon-based input set may include at least one of the following sets of surgical variables (SVs) related to the region of interest: a first set of surgical variables linked to a first region of interest, wherein each surgical variable from the first set of surgical variables has a range of acceptable values ​​ideally defined by the surgeon within a range of acceptable values ​​defined by the manufacturer; a second set of surgical variables linked to a second region of interest, wherein each surgical variable from the second set of surgical variables has a range of acceptable values ​​ideally defined by the surgeon within a range of acceptable values ​​defined by the manufacturer; a third set of surgical variables linked to a third region of interest, wherein each surgical variable from the third set of surgical variables has a range of acceptable values ​​ideally defined by the surgeon within a range of acceptable values ​​defined by the manufacturer; or More generally, there are "n" sets of surgical variables linked to "n" regions of interest, where each surgical variable from the "n" sets of surgical variables has a range of acceptable values ​​ideally defined by the surgeon, within a range of acceptable values ​​defined by the manufacturer.

[0043] It should be noted that sets of surgical variables can be linked to regions of interest, and there may be a level of interdependence where a given surgical variable may be linked to multiple regions of interest. For example, incision orientation as a surgical variable may affect both alignment and soft tissue tension, in other words, two different regions of interest.

[0044] In some embodiments, the region of interest may include at least one of the following sets of patient-specific functional parameters (FPs) associated with the region of interest: a first set of functional parameters linked to the first region of interest, wherein each functional parameter from the first set of functional parameters has a target value range ideally defined by the surgeon within a range of tolerance values ​​defined by the manufacturer; a second set of functional parameters linked to a second region of interest, wherein each functional parameter from the first set of functional parameters has a target value range ideally defined by the surgeon within a range of tolerance values ​​defined by the manufacturer; a second set of functional parameters linked to a second region of interest, wherein each functional parameter from the second set of functional parameters has a target value range ideally defined by the surgeon within a range of tolerance values ​​defined by the manufacturer; a third set of functional parameters linked to a third region of interest, wherein each functional parameter from the third set of functional parameters has a target value range ideally defined by the surgeon within a range of allowed values ​​defined by the manufacturer; or More generally, there are "n" sets of functional parameters linked with "n" regions of interest, where each functional parameter from the "n" sets of functional parameters has a target value range, ideally defined by the surgeon, within a range of allowed values ​​defined by the manufacturer.

[0045] In some embodiments, the system can utilize a healthcare-based input set that may include at least one of the following data: · payer insurance type; a hospital or outpatient surgery center, or Rehabilitation type

[0046] At least one aspect of at least one embodiment disclosed herein is that at least one algorithm used therein can generate a personalized surgical plan that considers functional parameters as goals to be achieved as outputs through processing of surgical variables applied to a patient-based input set, and because it is likely that all functional parameters will not be achieved simultaneously, weights can be assigned between different regions of interest, and the regions of interest can be ranked according to order of importance.

[0047] In some embodiments, at least some embodiments disclosed herein further define the setup of weights for one or more algorithms, including but not limited to machine learning based algorithms, and their impact on the definition of the surgical plan.

[0048] In some embodiments, the weighting approach can facilitate the possibility of highlighting specific regions of interest (e.g., alignment, size, joint laxity, or resection thickness, or any combination thereof) based on a surgical workflow selected by the surgeon, and / or by patient-based criteria, and / or by any other input.

[0049] In some embodiments, the weights for each region of interest and subsequently each functional parameter may be determined by a number of approaches.

[0050] In some embodiments, a weight-based implant algorithmic model, a weight-based implant (trained) machine learning model, or both may be used in combination with objectively determining the weights or ranking them in order of importance (e.g., #1, #2, #3, ...) and / or expressed in subjective terms (e.g., high, medium, low). This ranking or prioritization may also be referred to herein as patient-specific functional parameter prioritization.

[0051] In some embodiments, the weight-based implant algorithm model, the weight-based implant (trained) machine learning model, or both may rank each functional parameter based on its weight according to a workflow. For example, in the case of a mechanical alignment-based total knee arthroplasty (TKA), the weight-based implant algorithm model, the weight-based implant (trained) machine learning model, or both may prioritize alignment-based parameters over laxity-based parameters and size-based parameters. Similarly, in the case of a functional alignment-based total knee arthroplasty (TKA), the weight-based implant algorithm model, the weight-based implant (trained) machine learning model, or both may prioritize laxity-based parameters over alignment-based parameters and size-based parameters.

[0052] In some embodiments, a surgical procedure (not limited to a knee surgical procedure) may incorporate at least one type of joint alignment procedure, and the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both may output a plurality of weights based at least in part on the at least one type of joint alignment procedure.

[0053] In some embodiments, the at least one type of joint alignment procedure is based on at least one of mechanical alignment, anatomical alignment, kinematic alignment, constrained kinematic alignment, inverse kinematic alignment, or functional alignment.

[0054] In some embodiments, if the at least one type of joint alignment procedure is mechanical alignment, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both may output at least one implant alignment weight having the highest weight.

[0055] In some embodiments, if at least one type of joint alignment procedure is functional alignment, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both may output at least one joint laxity weight having the highest weight.

[0056] In some embodiments, if the at least one type of joint alignment procedure is kinematic alignment, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both may output at least one implant resection thickness weight with the highest weight.

[0057] FIG. 6 is a table 300 illustrating data for a surgical plan setup for a TKA considering alignment, size, and joint laxity as areas of interest in accordance with one or more embodiments of the present disclosure.

[0058] In some embodiments, with respect to FP weights, consider an exemplary embodiment of a total knee replacement for three regions of interest: alignment, size, and laxity, and define the corresponding weights of these regions of interest as W, ... a ,W s ,W i The weights can be expressed as: By assigning these weights, the algorithm can assign planned surgical variables across the spectrum of all surgical variables to maximize the performance of FPs associated with regions of interest with higher weights over FPs associated with regions of interest with lower weights. Maximizing the degree of fulfillment may refer to how closely the FPs of a particular region of interest can be brought to their respective goals. In other embodiments, maximizing the degree of fulfillment may refer to how closely the FPs of a particular region of interest can be brought to their respective targets based on the weights. In yet other embodiments, maximizing the degree of fulfillment may refer to how closely the FPs of a particular region of interest can be brought to their respective targets based on the ranking of the weights.

[0059] In some embodiments, the alignment, size, and laxity FP are respectively (A1, A2, ..., A M ), (S1,S2,...,S N ), and (L1,L2,...,L P ) The objective is to minimize the overall global error contributed by the FP across various regions of interest. In this exemplary embodiment, three regions of interest can be considered: alignment, size, and laxity. Alignment (w a ), size (w s ), and flaccidity (w l ) is a global error function Err(FP, w a , w s , w l ) may be given to: TIFF2025183161000002.tif33150

[0060] In some embodiments, each err(FP i ) may denote an error penalty function designed to ensure that the fitted FP falls within a specified threshold. A custom piecewise linear penalty function is used to i ) is constrained to be within the target and tolerance thresholds. The linear penalty function for FPx is given as follows: TIFF2025183161000003.tif31142

[0061] TIFF2025183161000004.tif36150

[0062] In some embodiments, an alternative error penalty function, such as a quadratic, cubic, exponential, or sigmoid function, can be applied instead of a linear penalty function to change the error penalty rate from the linear penalty function when the FP deviates from the tolerance threshold.

[0063] TIFF2025183161000005.tif43150

[0064] In some embodiments, the optimization process is performed using a global error function Err(FP, w a , w s , w l ) and find the optimal weights w based on the data. a ,w s ,w l The optimization algorithm can adjust the weights by assigning lower weights to regions of interest with larger FP errors and higher weights to regions of interest with smaller FP errors. In this way, higher weights correspond to a narrower range of FPs, and lower weights correspond to a wider range of FPs. An example of an optimization algorithm training to determine optimal weights may be provided in the Surgeon-Specific Functional Parameter Optimization Model (FPOM) section of this specification.

[0065] In some embodiments, the regions of interest are ranked based on the magnitude of their weights, with priority given to regions of interest with the highest weights. Functional parameters associated with regions with higher weights are likely to be better satisfied than the FPs of subsequent regions of interest based on their rank. For example, a =0.7, w s =0.1, w l = 0.2, the ranking of areas of concern from most important to least important is alignment > laxity > size. Alignment FPs are more likely to be satisfied than planning laxity FPs, and then size FPs.

[0066] 8 illustrates functional parameter (FP) workflows for an expert and an inexperienced surgeon, in accordance with one or more embodiments of the present disclosure, where "expert" may refer to the surgeon's clinical experience (i.e., the number of cases the surgeon has previously performed).

[0067] In some embodiments, FIG. 8 allows for weighting of the three regions of interest, alignment, size, laxity, and / or resection thickness, to be personalized to the surgeon's requirements for a particular surgical case. a , w s , wl 3 illustrates a workflow 315 for obtaining an input 350. The input 350 can be from multiple sources, for example, but not limited to: - Functional parameters (FP): FPs related to surgeon-specific areas of interest such as alignment, size, laxity, and resection thickness. -Surgeon Workflow (SW) category: For example, in the case of TKA, there are countless possible workflow combinations based on the osteotomy order (tibia-first, femur-first, etc.) and alignment technique (mechanical alignment, kinematic alignment, functional alignment, etc.). -Patient information: demographics, area of ​​residence, activity, deformity category, etc.

[0068] In some embodiments, the workflow 315 can begin with a check 320 of the number of previous cases (num cases) available to the surgeon. A predefined threshold T representing a minimum number of cases can be used to classify skilled surgeons 330 and unskilled surgeons 325.

[0069] In some embodiments, for a skilled surgeon 330, the optimal weight w a , w s , w l A trained surgeon-specific FPOM with 335 can be used to predict surgical variables 340 for a particular case.

[0070] In some embodiments, for the unskilled surgeon 325, the optimal weight w a , w s , w l The most relevant FPOM model with the weights can be searched from the expert surgeon database to predict the surgical variables for a particular case. If no model can be found, a default model 355 with predefined weights can be used to predict the surgical variables.

[0071] It is noted that in the context of the present disclosure, a model may be relevant if it is trained using data that matches or closely aligns with the combination of inputs provided for the current use case, thereby increasing the likelihood that the model's output (e.g., recommendation weights) will be applicable and / or useful for the intended surgical plan.

[0072] In some embodiments, the relevance of the models may be determined directly based on matching attributes (e.g., the same surgical workflow) or through a similarity measure calculated by clustering techniques when multiple inputs may be related. In use case scenarios where partial matches may exist, relevance may be assessed based on the degree of overlap and proximity of the inputs within the clustering hierarchy.

[0073] In some embodiments, if the minimum case count condition 320 is not met (e.g., for a non-expert surgeon 325), one or more inputs described herein may be utilized to search the expert surgeon database 345 to find the model 360 most relevant to the non-expert surgeon's particular case. As an illustrative example, but not limited to, if only the surgeon workflow (SW) is available (e.g., TKA, tibia first, mechanical alignment), the search attribute SW may be used to find the model. Note: It may be possible to search for models from input sizes ranging from 1 to I, where I is the maximum size of the input available. If no relevant models are found, a default configuration setup 355 based on the surgeon's philosophy may be utilized. For example, if the surgeon cares about alignment and size and does not care about looseness, more weight may be assigned to alignment and size, and zero weight may be assigned to looseness.

[0074] In some embodiments, if the minimum case volume condition 320 is met (e.g., for an expert surgeon), all available inputs from the aforementioned input sources can be collected. These inputs can be provided to a surgeon-specific trained FPOM model 335 with optimal weights to predict surgical variables 340.

[0075] In some embodiments, the multiple models of expert surgeons may be based on several factors such as, but not limited to, the number of inputs, the amount of training data, the area of ​​interest, and other attributes such as, for example, but not limited to: Inputs: Different models can be trained and tested on various combinations of inputs. For example, there could be a model based only on patient deformations, a model based on a combination of SW and patient input, a model based on a particular FP of interest, etc. Amount of training data: Models may be built or updated based on the amount of training data. Areas of interest: Multiple models can be trained based on different areas of interest for the same surgeon. For example, one model may prioritize alignment and focus on cases where alignment goals are a priority, while another model may emphasize laxity.

[0076] In some embodiments, the weight-based implant algorithm, the weight-based implant machine learning model, or both, may be generated based at least in part on surgeon-specific data stored in an expert surgeon database. The surgeon-specific data may be based on a combination of inputs (e.g., workflow, patient factors, etc.), the amount of training data (e.g., all past cases, last N cases, first M cases), and / or a preference for one or more regions of interest (e.g., alignment-focused vs. laxity-focused).

[0077] In some embodiments, the plurality of weights output from the weight-based implant algorithm, the weight-based implant machine learning model, or both, for a surgical procedure performed by at least one expert surgeon may be trained using surgeon-specific data from past personalized cases of the at least one expert surgeon.

[0078] In some embodiments, the multiple weights output from the weight-based implant algorithm, the weight-based implant machine learning model, or both, for a surgical procedure performed by at least one junior, unskilled surgeon may be learned from a generalized model based on surgical workflow relevance, patient-specific inputs, etc.

[0079] 9 illustrates FPOM algorithm training using batch gradient descent optimization pseudocode 375 that considers three regions of interest: alignment, size, and relaxivity, in accordance with one or more embodiments of the present disclosure. The training and testing (model evaluation) process is described below in FIG. 10. The training process and FPOM algorithm are further described below.

[0080] In some embodiments, other optimization methods may be used to determine the optimal weights, such as, but not limited to, mini-batch gradient descent, stochastic gradient descent, adaptive gradient algorithm (Adagrad), root mean square propagation (RMSprop), etc.

[0081] In some embodiments, for a surgeon-specific FPOM algorithm, FPOM algorithm training pseudocode may be provided in Figure 9. The FPOM may be trained using expert surgeon data, as previously described herein. The goal of FPOM training is to determine optimal weights based on the training data and available inputs, as follows: The training dataset may contain data from t cases. For each training case, the implant fit method can calculate all possible implant positions to calculate the matching FPs such that each FP meets the tolerance and target thresholds. It can select the optimal plan from the entire available matching space to minimize the global error for each case. This process can be repeated to calculate the global error for all training cases. An optimization method, such as batch gradient descent, can be applied to calculate optimal weights based on all training samples.

[0082] Note that the FPOM model can be used synonymously with the weight-based implant algorithm.

[0083] In some embodiments, a weight-based implant algorithm that outputs a plurality of weights may be implemented as a machine learning model, and is referred to herein as a weight-based implant machine learning model.

[0084] FIG. 10 is a block diagram 600 illustrating training and model evaluation of an FPOM model according to one or more embodiments of the present disclosure. Regarding FPOM training and evaluation, the training and model evaluation (testing) of the FPOM model are illustrated in FIG. 10, but the error metrics for training and testing may be the same as those illustrated in FIG. 9. For T cases available to an experienced surgeon, the dataset is randomly split into training data 382 and test data 385, with training size (t) and test size (Tt), respectively. The training / test split ratio can be, for example, 80 / 20 or 90 / 10, depending on the availability of the dataset.

[0085] In some embodiments, weight-based multiple implementation modes may be assigned to the n regions of interest. Using exemplary embodiments, an evaluation is performed to determine how an alternative mode (e.g., relaxation-based planning) may compare to a common default mode (e.g., alignment-based planning), which may assist some surgeons in planning.

[0086] In some embodiments, a dataset containing, for example, 313 total knee arthroplasty (TKA) cases performed by six surgeons using the full gap balancing method can be used to test these implementation modes. For comparison, two modes can be established: a) a mode that prioritizes alignment and size and de-weights laxity (high weighting on alignment and size, low weighting on laxity); and b) a mode that, conversely, prioritizes laxity and size, and de-weights alignment. Within the scope of this disclosure, these two modes may be referred to as the history algorithm and the laxity-based algorithm.

[0087] In some embodiments, after obtaining the joint gap over the entire arc of motion in a force-controlled environment for each case, the algorithm outputs a preliminary femoral surgery plan (initial plan), which can then be personalized by the surgeon (final plan).

[0088] In some embodiments, for each algorithm, the total number of adjustment clicks for each of the nine cutting parameters required to move from the initial plan suggested by each algorithm to the final plan verified by the surgeon may be calculated, where adjustment clicks may represent the number of screen interactions by the surgeon indicating a 1 mm / 1 deg change.

[0089] In some embodiments, surgical planning algorithms can be used to improve the setup of such plans. In this regard, one study reviewed the technical logs of 313 TKA cases performed by six surgeons using the full gap balancing method. For each case, after obtaining the joint gap across the entire arc of motion in a force-controlled environment, an algorithm was used to generate a preliminary femoral surgical plan (initial plan), which was then personalized by the surgeon (final plan). Two different algorithms were considered for the setup of the initial plan: (1) a history-based algorithm based solely on alignment and size considerations, and (2) a laxity-based algorithm based solely on soft tissue and size considerations. For each algorithm, the total number of adjustment clicks for each of the nine cutting parameters required to transition from the initial plan proposed by each algorithm to the final plan verified by the surgeon can be calculated. Adjustment clicks represent the number of screen manipulations by the surgeon, representing a 1 mm / 1 degree change.

[0090] Although the algorithm flow described above may refer to three regions of interest: alignment, size, and laxity, this is not intended to limit the embodiments disclosed herein. The algorithm flow may include any number of regions of interest. For example, implant resection thickness and corresponding weight may be another region of interest that may be included in the algorithm flow and weight prioritization described herein. Thus, at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both may: at least one implant alignment weight for at least one implant alignment functional parameter of the plurality of patient-specific functional parameters; at least one implant size weight for at least one implant size functional parameter of the plurality of patient-specific functional parameters; at least one joint laxity weight for at least one joint laxity functional parameter of the plurality of patient-specific functional parameters; at least one implant resection thickness weight for at least one implant resection thickness functional parameter of the plurality of patient-specific functional parameters; or any combination thereof, The weighting factor may output a plurality of weights, which may include at least one of:

[0091] It should be noted that in the context of this disclosure, the definition of "size" may be the overall fit between the implant and the bone, and therefore may include dimensional considerations such as (1) the resection thickness of different bone cuts (e.g., proximal femoral cut, distal femoral cut, posterior condylar cut), (2) the anterior-posterior fit of the implant to the bone members, (3) the medial-lateral fit of the implant to the bone members, or (4) any other linear dimension typically expressed in millimeters or inches.

[0092] 11A-11C are table 390 illustrating the difference in the number of adjustment clicks required by surgeons when employing a history algorithm versus a laxity-based planning algorithm, in accordance with one or more embodiments of the present disclosure. Specifically, the number of adjustment clicks for six surgeons and nine cutting parameters calculated using the history algorithm is shown in FIG. 11A, while the number of adjustment clicks calculated using the laxity-based planning algorithm is shown in FIG. 11B. FIG. 11C illustrates the percentage reduction in adjustment clicks. Laxity-based planning significantly improved the definition of the initial plan, with the average number of adjustment clicks decreasing by 38.5% (range 18.7-70.2%) from 12.93 clicks (range 8.57-18.62) using the history algorithm to 7.95 clicks (range 5.54-10.0) using the laxity-based algorithm. The results of this analysis may indicate that some surgeons may find it advantageous to utilize an alternative implementation method, such as laxity-based planning, which emphasizes laxity compared to traditional alignment-prioritized approaches.

[0093] Historically, TKA procedures have been systematic and heavily based on predefined alignment goals. As a result, corresponding planning algorithms have similarly focused on alignment. The recognition of the importance of optimizing soft-tissue balance in TKA allows surgeons to target patient-centered surgical planning. This study illustrates the potential of laxity-based planning to support surgeons in performing personalized TKA.

[0094] While the present disclosure utilizes a total knee joint where the algorithm may be utilized for femoral surgical planning setup, this approach may also be applied to other partial or total knee applications, as well as other surgical workflows.

[0095] In some embodiments, the joints considered may be described as any joint that may include at least a first bone member and at least a second bone member, such as, but not limited to, an elbow, shoulder, hip, knee, and / or ankle. It should be noted that some of these joints may include three bone members. For example, the elbow joint is composed of the proximal humerus and both the distal ulna and radius. Also, some of these joints may include accessory joints. For example, the knee joint may include both the tibiofemoral joint between the femur (thigh bone) and the tibia (shin bone) and the patellofemoral joint between the patella (kneecap) and the femur (thigh bone).

[0096] Furthermore, the algorithms described herein can be applied to both partial and total joint replacements. Partial joint replacements can involve replacing / surfacing only one side of a joint, while total joint replacements can involve replacing / surfacing the entire joint. For example, partial knee replacements (PKA) or unicompartmental knee replacements (UKA) can involve resurfacing only one compartment of the knee joint (i.e., medial or lateral), while total knee replacements (TKA) can involve simultaneous resurfacing of both compartments of the knee joint (i.e., medial and lateral).

[0097] In some embodiments, the algorithms described herein may be applied to hemiarthroplasty indications, where one bony member of the joint under consideration may be replaced / resurfaced. For example, a hemiarthroplasty of the shoulder joint may involve replacing / resurfaced the humeral head while preserving the native glenoid cavity.

[0098] Finally, depending on the surgical workflow, the algorithms described herein may be applied to one bone member or to at least two bone members. For example, in some embodiments, during surgery, a surgeon may acquire a first set of patient-specific data (e.g., anatomical landmarks, joint laxity), prepare a first bone member, acquire a second set of patient-specific data, and utilize these sets of data as input to an algorithm that provides a surgical plan for the preparation of at least a second bone member. In other embodiments, during surgery, a surgeon may acquire a set of patient-specific data (e.g., anatomical landmarks, joint laxity), and utilize this set of data as input to an algorithm that provides a surgical plan for the preparation of at least two bone members. It should be noted that these embodiments may be combined, such that during surgery, a surgeon may acquire a patient-specific data set (e.g., anatomical landmarks, joint laxity), utilize this data set as input to an algorithm described above to provide a surgical plan for the preparation of at least two bone members, prepare a first bone member, acquire a patient-specific second set of data, and utilize this second set of data as input to refine an initially proposed surgical plan for the preparation of at least a second bone member.

[0099] In some embodiments, exemplary inventive specially programmed computing systems / platforms with associated devices may operate in a distributed network environment, communicating with each other over one or more suitable data communication networks (e.g., the Internet, satellite, etc.), utilizing one or more suitable data communication protocols / modes such as, but not limited to, IPX / SPX, X.25, AX.25, AppleTalk®, TCP / IP (e.g., HTTP), Near Field Communication (NFC), RFID, Narrow Band Internet of Things (NBIOT), 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, and other suitable communication modes.

[0100] The material disclosed herein may be implemented as software or firmware, or a combination thereof, or as instructions stored on a machine-readable medium, which may be read and executed by one or more processors. A machine-readable medium may include any medium and / or mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). For example, a machine-readable medium may include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, electrical, optical, acoustical, or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), etc.

[0101] As used herein, the terms "computer engine" and "engine" identify at least one software component and / or a combination of at least one software component and at least one hardware component designed / programmed / configured to manage / control other software and / or hardware components (libraries, software development kits (SDKs), objects, etc.).

[0102] Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, etc.), integrated circuits, application specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field programmable gate arrays (FPGAs), logic gates, registers, semiconductor devices, chips, microchips, chipsets, etc. In some embodiments, one or more processors may be implemented as a complex instruction set computer (CISC) or reduced instruction set computer (RISC) processor, an x86 instruction set compatible processor, a multi-core, or any other microprocessor or central processing unit (CPU). In various implementations, one or more processors may be dual-core processors, dual-core mobile processors, etc.

[0103] As used herein, computer-related system, computer system, and system include any combination of hardware and software. Examples of software may include software components, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (APIs), instruction sets, computer code, computer code segments, words, values, symbols, or any combination thereof. The decision of whether an embodiment is implemented using hardware and / or software elements may vary according to any number of factors, such as desired computational speed, power levels, thermal tolerances, processing cycle budgets, input data rates, output data rates, memory resources, data bus speeds, and other design or performance constraints.

[0104] One or more aspects of at least one embodiment may be implemented by representative instructions stored on a machine-readable medium that represent various logic within a processor, which, when read by a machine, causes the machine to create logic that performs the techniques described herein. Such representations, known as "IP cores," may be stored on tangible machine-readable media and supplied to various customers or manufacturing facilities for loading into manufacturing machines that produce the logic or processors. Of course, the various embodiments described herein may be implemented using any suitable hardware and / or computing software language (e.g., C++, Objective-C, Swift, Java, JavaScript, Python, Perl, QT, etc.).

[0105] In some embodiments, one or more of the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may include or combine at least one personal computer (PC), laptop computer, ultranotebook computer, tablet, touchpad, portable computer, handheld computer, palmtop computer, personal digital assistant (PDA), mobile phone, mobile phone / PDA combination, television, smart device (e.g., smartphone, smart tablet, smart TV), mobile internet device (MID), messaging device, data communication device, etc.

[0106] As used herein, the term "server" should be understood to refer to a service point that provides processing, database, and communication facilities. By way of example and not limitation, the term "server" may refer to a single physical processor with associated communication, data storage, and database facilities, or it may refer to a complex of networked or clustered processors, associated networks and storage, as well as operating software and one or more database systems and application software that support the services provided by the server. A cloud server is one example.

[0107] In some embodiments, as detailed herein, one or more of the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may retrieve, manipulate, transfer, store, convert, generate, and / or output any digital objects and / or data units (e.g., from within and / or outside a particular application), which may be in any suitable format, such as, but not limited to, files, contacts, tasks, emails, social media posts, maps, entire applications (e.g., calculators), etc. In some embodiments, as detailed herein, one or more of the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may be implemented across one or more of a variety of computer platforms, including, but not limited to, the following: (1) FreeBSD, NetBSD, OpenBSD, (2) Linux, (3) Microsoft Windows, (4) OS X (MacOS), (5) MacOS 11, (6) Solaris, (7) Android, (8) iOS, (9) Embedded Linux, (10) Tizen, (11) WebOS, (12) IBM i, (13) IBM AIX, (14) Wireless Binary Execution Environment (BREW), (15) Cocoa (API), (16) Cocoa Touch, (17) Java Platform, (18) JavaFX, (19) JavaFX Mobile, (20) Microsoft DirectX, (21) .NET Framework, (22) Silverlight, (23) Open Web Platform, (24) Oracle Database, (25) Qt, (26) Eclipse Rich Client Platform, (27) SAP NetWeaver, (28) Smartface, and / or (29) Windows Runtime.

[0108] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may utilize hardwired circuitry that may be used in place of or in combination with software instructions to implement features consistent with the principles of the present disclosure. Thus, implementations consistent with the principles of the present disclosure are not limited to any particular combination of hardware circuitry and software. For example, various embodiments may be embodied in many different ways as a software component, including, but not limited to, a standalone software package, a combination of software packages, or a software package incorporated as a "tool" in a larger software product.

[0109] For example, exemplary software specifically programmed in accordance with one or more principles of the present disclosure may be downloadable from a network, e.g., a website, as a standalone product or as an add-in package for installation into an existing software application. For example, exemplary software specifically programmed in accordance with one or more principles of the present disclosure may also be available as a client-server software application or as a web-enabled software application. For example, exemplary software specifically programmed in accordance with one or more principles of the present disclosure may also be embodied as a software package installed on a hardware device.

[0110] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure can handle a large number of concurrent users, such as at least 100 (e.g., but not limited to, 100-999), at least 1,000 (e.g., but not limited to, 1,000-9,999), at least 10,000 (e.g., but not limited to, 10,000-99,999), at least 100,000 (e.g., but not limited to, 100, 999,999), at least 1,000,000 (for example, but not limited to, 1,000,000 to 9,999,999), at least 10,000,000 (for example, but not limited to, 10,000,000 to 99,999,999), at least 1,000,000,000 (for example, but not limited to, 100,000,000 to 999,999,999), at least 1,000,000,000 (for example, but not limited to, 1,000,000,000 to 999,999,999,999).

[0111] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may output to a separate, specifically programmed graphical user interface embodiment of the present disclosure (e.g., desktop, web app, etc.). In various embodiments of the present disclosure, the final output may be displayed on a display screen, which may be, but is not limited to, a computer screen, a mobile device screen, etc. In various embodiments, the display may be a holographic display. In various embodiments, the display may be a transparent surface capable of receiving a visual projection. Such projections may convey various forms of information, images, and / or objects. For example, such projections may be visual overlays for mobile augmented reality (MAR) applications.

[0112] As used herein, terms such as "portable electronic device" may refer to any portable electronic device that may or may not be enabled for location tracking capabilities (e.g., MAC address, Internet Protocol (IP) address, etc.) For example, a portable electronic device may include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a smartphone, or other reasonable portable electronic device.

[0113] As used herein, the terms “proximity detection,” “location determination,” “location data,” “location information,” and “location tracking” refer to any form of location tracking technology or location determination method that can be used to provide, for example, the location of a particular computing device / system / platform of the present disclosure, and / or any associated computing devices, based at least in part on one or more of the following technologies / devices, without limitation: The present invention may utilize various techniques, such as accelerometers, gyroscopes, global positioning systems (GPS), GPS accessed using Bluetooth®, GPS accessed using any reasonable wireless and / or non-wireless communication, Wi-Fi server location data, Bluetooth®-based location data, network-based triangulation, Wi-Fi server information-based triangulation, Bluetooth® server information-based triangulation, cellular identification-based triangulation, enhanced cellular identification-based triangulation, triangulation such as uplink time difference of arrival (U-TDOA)-based triangulation, time of arrival (TOA)-based triangulation, angle of arrival (AOA)-based triangulation, RFID such as long-range RFID, short-range RFID, RFID tags such as active RFID tags, passive RFID tags, battery-assisted passive RFID tags, or other reasonable methods of determining location. For simplicity, the above variations may not be listed or may only be partially listed, but this is in no way meant to be limiting.

[0114] As used herein, the terms "cloud," "Internet cloud," "cloud computing," "cloud architecture," and similar terms correspond to at least one of the following: (1) a large number of computers connected via a real-time communications network (e.g., the Internet); (2) the provision of the ability to simultaneously run programs or applications on a large number of connected computers (e.g., physical machines, virtual machines (VMs)); or (3) network-based services that appear to be provided by actual server hardware but are actually provided by virtual hardware (e.g., virtual servers) and simulated by software running on one or more actual machines (e.g., services that can be moved on the fly and scaled up (or down) without impacting end users).

[0115] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may utilize one or more of the following encryption techniques to securely store and / or transmit data: Private / public key pairs, Triple Data Encryption Standard (3DES), block cipher algorithms (e.g., IDEA, RC2, RC5, CAST, Skipjack), cryptographic hash algorithms (e.g., MD5, RIPEMD-160, RTR0, SHA-1, SHA-2, Tiger (TTH), WHIRLPOOL, RNG).

[0116] Of course, the above examples are illustrative and not limiting.

[0117] As used herein, the term "user" shall mean at least one user. In some embodiments, the terms "user," "subscriber," "consumer," or "customer" shall be understood to refer to a user of an application or applications described herein and / or a consumer of data provided by a data provider. By way of example and not limitation, the terms "user" or "subscriber" may refer to a person receiving data over the Internet in a browser session or data provided by a service provider, or may refer to an automated software application that receives data and stores or processes the data.

[0118] FIG. 12 illustrates a block diagram of an exemplary computer-based system / platform 400 in accordance with one or more embodiments of the present disclosure. However, not all of these components may be required to practice one or more embodiments, and variations in the arrangement and type of components may be made without departing from the spirit or scope of various embodiments of the present disclosure. In some embodiments, the exemplary inventive computing devices and / or exemplary inventive computing components of the exemplary computer-based system / platform 400 may be configured to manage a large number of members and / or concurrent transactions, as detailed herein. In some embodiments, the exemplary computer-based system / platform 400 may be based on a scalable computer and / or network architecture incorporating various strategies for data evaluation, caching, retrieval, and / or database connection pooling. An example of a scalable architecture is one capable of operating multiple servers.

[0119] 12 , members 402-404 (e.g., clients) of exemplary computer-based system / platform 400 may include virtually any computing device capable of receiving and transmitting messages to and from another computing device, such as servers 406 and 407, each other, and the like, over a network (e.g., a cloud network) such as network 405. In some embodiments, member devices 402-404 may be personal computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, and the like. In some embodiments, one or more member devices within member devices 402-404 may include computing devices that typically connect using a wireless communication medium, such as a cell phone, a smartphone, a pager, a walkie-talkie, a radio frequency (RF) device, an infrared (IR) device, CB, an integrated device combining one or more of the foregoing devices, or virtually any mobile computing device. In some embodiments, one or more of the member devices 402-404 may be a PDA, pocket PC, wearable computer, laptop, tablet, desktop computer, netbook, video game device, pager, smartphone, ultra-mobile personal computer (UMPC), and / or any other device equipped to communicate via a wired and / or wireless communication medium (e.g., NFC, RFID, NBIOT, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, etc.). In some embodiments, one or more of the member devices 402-404 may run one or more applications such as an internet browser, mobile applications, voice calls, video conferencing, and email, among others. In some embodiments, one or more of the member devices 402-404 may receive and send web pages, etc.In some embodiments, an exemplary specifically programmed browser application of the present disclosure may employ virtually any web-based language to receive and display graphics, text, multimedia, etc., including, but not limited to, Standard Generalized Markup Language (SMGL) such as Hypertext Markup Language (HTML), Wireless Application Protocol (WAP), Handheld Device Markup Language (HDML) such as Wireless Markup Language (WML), WMLScript, XML, JavaScript, etc. In some embodiments, the member devices in member devices 402-404 may be specifically programmed in any of Java, .Net, QT, C, C++, and / or other suitable programming languages.

[0120] In some embodiments, exemplary network 405 can provide network access, data transmission, and / or other services to any computing devices coupled thereto. In some embodiments, exemplary network 405 can include and implement at least one specialized network architecture, which can be based at least in part on one or more standards established by, for example, but not limited to, the Global System for Mobile Communications (GSM) Association, the Internet Engineering Task Force (IETF), and the Worldwide Interoperability for Microwave Access (WiMAX) Forum. In some embodiments, exemplary network 405 can implement one or more of the GSM architecture, the General Packet Radio Service (GPRS) architecture, the Universal Mobile Telecommunications System (UMTS) architecture, and an evolution of UMTS called Long Term Evolution (LTE). In some embodiments, and optionally in combination with any of the embodiments described above or below, exemplary network 405 can also include, for example, at least one of a local area network (LAN), a wide area network (WAN), the Internet, a virtual LAN (VLAN), a corporate LAN, a Layer 3 virtual private network (VPN), a corporate IP network, or any combination thereof. In some embodiments, and optionally in combination with any embodiment described above or below, at least one computer network communication over exemplary network 405 may be transmitted based at least in part on one or more communication modes such as, but not limited to, NFC, RFID, Narrowband IoT (NBIOT), ZigBee, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, and any combination thereof. In some embodiments, exemplary network 405 may also include mass storage devices such as network-attached storage (NAS), storage area networks (SAN), content delivery networks (CDN), or other forms of computer- or machine-readable media.

[0121] In some embodiments, exemplary server 406 or exemplary server 407 may be a web server (or a series of servers) running a network operating system, examples of which include, but are not limited to, Microsoft Windows Server, Novell NetWare, or Linux. In some embodiments, exemplary server 406 or exemplary server 407 may be used for and / or provided for cloud computing and / or network computing. Although not shown in FIG. 12 , in some embodiments, exemplary server 406 or exemplary server 407 may have connections to external systems such as email, SMS messaging, text messaging, advertising content providers, etc. Any of the features of exemplary server 406 may also be implemented in exemplary server 407, and vice versa.

[0122] In some embodiments, and optionally in combination with any of the embodiments described above or below, for example, one or more of exemplary computing member devices 402-404, exemplary server 406, and / or exemplary server 407 may include specially programmed software modules that may send, process, and receive information using a scripting language, may include specially programmed software modules that may send, process, and receive information using a scripting language, remote procedure calls, email, tweets, short message service (SMS), multimedia message service (MMS), instant messaging (IM), Internet Relay Chat (IRC), mIRC, Jabber, application programming interfaces, Simple Object Access Protocol (SOAP) methods, Common Object Request Broker Architecture (CORBA), HTTP (Hypertext Transfer Protocol), REST (Representational State Transfer), or any combination thereof.

[0123] FIG. 13 shows a block diagram of another exemplary computer-based system / platform 500 in accordance with one or more embodiments of the present disclosure. However, not all of these components may be required to practice one or more embodiments, and variations in the arrangement and type of components may be made without departing from the spirit or scope of various embodiments of the present disclosure. In some embodiments, the illustrated member computing devices 502 a, 502 b, through 502 n each include at least a computer-readable medium, such as a processor 510 or random access memory (RAM) 508 coupled to a flash memory. In some embodiments, the processor 510 can execute computer-executable program instructions stored in the memory 508. In some embodiments, the processor 510 may include a microprocessor, an ASIC, and / or a state machine. In some embodiments, the processor 510 may include or be in communication with a medium, e.g., a computer-readable medium, that stores instructions that, when executed by the processor 510, can cause the processor 510 to perform one or more steps described herein. In some embodiments, examples of computer-readable media may include, but are not limited to, electronic, optical, magnetic, or other storage or transmission devices capable of providing computer-readable instructions to a processor, such as processor 510 of client 502a. In some embodiments, other examples of suitable media may include, but are not limited to, floppy disks, CD-ROMs, DVDs, magnetic disks, memory chips, ROMs, RAMs, ASICs, configured processors, all optical media, all magnetic tapes or other magnetic media, or other media from which a computer processor can read instructions. Also, various other forms of computer-readable media may transmit or carry instructions to a computer, including routers, private or public networks, or other transmission devices or channels, both wired and wireless.In some embodiments, the instructions may include code in any computer programming language, including, for example, C, C++, Visual Basic, Java, Python, Perl, JavaScript, etc.

[0124] In some embodiments, examples of member computing devices 502a through 502n may include numerous external or internal devices such as a mouse, CD-ROM, DVD, physical or virtual keyboard, display, speakers, or other input or output devices (clients) may be any type of processor-based platform connected to network 506, such as, but not limited to, a personal computer, digital assistant, personal digital assistant, smartphone, pager, digital tablet, laptop computer, and other processor-based device. In some embodiments, member computing devices 502a through 502n may be specifically programmed with one or more application programs in accordance with one or more principles / methodologies detailed herein. In some embodiments, member computing devices 502a through 502n may operate on any operating system capable of supporting a browser or browser-enabled applications, such as Microsoft®, Windows®, and / or Linux. In some embodiments, the illustrated member computing devices 502a through 502n may include personal computers running browser application programs such as, for example, Microsoft Corporation's Internet Explorer®, Apple Computer's Safari®, Mozilla Firefox, and / or Opera. In some embodiments, through member computing client devices 502a through 502n, users 512a through 512n can communicate with each other and / or with other systems and / or devices coupled to network 506 via exemplary network 506. As shown in Figure 10, exemplary server devices 504 and 513 may also be coupled to network 506. In some embodiments, one or more of member computing devices 502a through 502n may be mobile clients.

[0125] In some embodiments, at least one of the exemplary databases 507 and 515 may be any type of database, including a database managed by a database management system (DBMS). In some embodiments, the database managed by the exemplary DBMS may be specifically programmed as an engine that controls the organization, storage, management, and / or retrieval of data within the respective database. In some embodiments, the exemplary DBMS-managed database may be specifically programmed to provide automated capabilities for querying, backup and replication, enforcing rules, providing security, performing calculations, change and access logging, and / or optimization. In some embodiments, the exemplary DBMS-managed database may be selected from Oracle Database, IBM DB2, Adaptive Server Enterprise, FileMaker, Microsoft Access, Microsoft SQL Server, MySQL, PostgreSQL, and NoSQL implementations. In some embodiments, the exemplary DBMS-managed database may be specifically programmed to define the respective schema of each database in the exemplary DBMS according to a particular database model of the present disclosure, which may include a hierarchical model, a network model, a relational model, an object model, or other suitable organization that may result in one or more applicable data structures that may include fields, records, files, and / or objects. In some embodiments, the exemplary DBMS-managed database may be specifically programmed to include metadata about the data stored therein.

[0126] In some embodiments, the exemplary computer-based systems / platforms, exemplary computer-based devices, and / or exemplary computer-based components of the present disclosure may specifically operate in a cloud computing / architecture, such as, but not limited to, Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and / or Software as a Service (SaaS). Figures 14 and 15 show schematic diagrams of exemplary implementations of cloud computing / architectures in which the exemplary computer-based systems / platforms, exemplary computer-based devices, and / or exemplary computer-based components of the present disclosure may specifically operate.

[0127] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may utilize one or more exemplary AI / machine learning techniques selected from, but not limited to, decision trees, boosting, support vector machines, neural networks, nearest neighbor algorithms, naive Bayes, bagging, random forests, etc. In some embodiments, and optionally in combination with any of the embodiments described above or below, the exemplary neural network technique may be one of, but not limited to, a feedforward neural network, a radial basis function network, a recurrent neural network, a convolutional network (e.g., a U-net), or other suitable networks. In some embodiments, and optionally in combination with any of the embodiments described above or below, an exemplary implementation of a neural network may be performed as follows: i) Define the neural network architecture / model, ii) forwarding the input data to an exemplary neural network model; iii) incrementally learning example models; iv) determining the accuracy for a particular number of time steps; v) applying the example trained model to process newly received input data; vi) Optionally, and in parallel, continue training the example trained model at a predetermined periodicity.

[0128] In some embodiments, and optionally in combination with any of the embodiments described above or below, the exemplary trained neural network model can specify the neural network by at least the neural network's topology, a set of activation functions, and connection weights. For example, the neural network's topology may include the configuration of the neural network's nodes and the connections between such nodes. In some embodiments, and optionally in combination with any of the embodiments described above or below, the exemplary trained neural network model can also be specified to include other parameters, including, but not limited to, bias values / functions and / or aggregation functions. For example, the activation function of a node may be a step function, a sine function, a continuous or piecewise linear function, a sigmoid function, a hyperbolic tangent function, or any other type of mathematical function that represents a threshold at which the node is activated. In some embodiments, and optionally in combination with any of the embodiments described above or below, the exemplary aggregation function may be a mathematical function that combines (e.g., sums, products, etc.) input signals to the node. In some embodiments, and optionally in combination with any of the embodiments described above or below, the output of the exemplary aggregation function may be used as input to the exemplary activation function. In some embodiments, and optionally in combination with any of the embodiments described above or below, the bias may be a constant value or function that may be used by the aggregation function and / or activation function to make a node more or less likely to be activated.

[0129] 16 shows a flowchart of a method 600 for implementing weight-based personalized implant planning during total joint arthroplasty in accordance with one or more embodiments of the present disclosure. In some embodiments, method 600 as a surgical method may be performed in conjunction with a surgeon, a processor or controller of a robotic surgical device, and / or processor 70 of controller 65.

[0130] In some embodiments, the method 600 may include obtaining 610 a plurality of pre-operative patient-specific data values ​​prior to implantation of at least one implant into a patient's joint including a first bone member and a second bone member.

[0131] In some embodiments, the method 600 may include inputting 620 the plurality of pre-operative patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, which outputs a plurality of weights assigned to the plurality of patient-specific functional parameters that facilitate prioritization of the plurality of patient-specific functional parameters.

[0132] In some embodiments, the method 600 may include utilizing 630 the surgical planning model to obtain a patient-specific intraoperative surgical plan for implantation of at least one implant based at least in part on the plurality of preoperative patient-specific data values, the plurality of patient-specific functional parameters, and the plurality of weightings, wherein the patient-specific intraoperative surgical plan comprises at least one surgical parameter based on a prioritization of the patient-specific functional parameters.

[0133] In some embodiments, the method 600 may include initiating 640 a surgical procedure for implantation based on a patient-specific intraoperative surgical plan.

[0134] In some embodiments, the method 600 may include inputting 650 a plurality of intraoperative patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, to generate a plurality of updated weights and a prioritization of the updated patient-specific functional parameters for the plurality of patient-specific functional parameters during the surgical procedure.

[0135] In some embodiments, the method 600 may include inputting 660 the plurality of updated weights, the plurality of intraoperative patient-specific data values, and the priority of the updated patient-specific functional parameters into the surgical planning model to obtain an updated intraoperative surgical plan having at least one updated surgical parameter during the surgical procedure.

[0136] In some embodiments, the method 600 may include preparing 670 the first bone member, the second bone member, or both based on the updated patient-specific intraoperative surgical plan to complete implantation of at least one implant during the surgical procedure.

[0137] In some embodiments, the method includes obtaining a plurality of pre-operative patient-specific data values ​​prior to implantation of at least one implant into a joint of the patient including a first bone member and a second bone member; inputting the plurality of pre-operative patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, that output a plurality of weights assigned to the plurality of patient-specific functional parameters that facilitate prioritization of the patient-specific functional parameters relative to the plurality of patient-specific functional parameters; and utilizing the surgical planning model to obtain a patient-specific intra-operative surgical plan for implantation of the at least one implant based at least in part on the plurality of pre-operative patient-specific data values, the plurality of patient-specific functional parameters, and the plurality of weights, wherein the patient-specific intra-operative surgical plan includes a patient-specific intra-operative surgical plan based on the at least one surgical parameter prioritization. inputting, during the surgical procedure, the plurality of intraoperative patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, to generate a plurality of updated weights for a plurality of patient-specific functional parameters and an updated patient-specific functional parameter prioritization; inputting, during the surgical procedure, the plurality of updated weights, the plurality of intraoperative patient-specific data values, and the updated patient-specific functional parameter prioritization into a surgical planning model to obtain an updated patient-specific intraoperative surgical plan having the at least one updated surgical parameter; and preparing, during the surgical procedure, the first bone member, the second bone member, or both, based on the updated patient-specific intraoperative surgical plan to complete the implantation of the at least one implant.

[0138] In some embodiments, the plurality of weights may include at least one of at least one implant alignment weight for at least one implant alignment functional parameter of the plurality of patient-specific functional parameters, at least one implant size weight for at least one implant size functional parameter of the plurality of patient-specific functional parameters, at least one joint laxity weight for at least one joint laxity functional parameter of the plurality of patient-specific functional parameters, at least one implant resection thickness weight for at least one implant resection thickness functional parameter of the plurality of patient-specific functional parameters, or any combination thereof.

[0139] In some embodiments, the at least one surgical parameter may be at least one of at least one surgical cutting parameter for the first bone member or the second bone member, or both, at least one implant alignment parameter, at least one implant size parameter, at least one joint laxity parameter, or any combination thereof.

[0140] In some embodiments, the plurality of pre-operative patient-specific data values ​​may include data from a plurality of patient-specific inputs, a plurality of surgeon-specific inputs, a plurality of practice-specific inputs, or any combination thereof.

[0141] In some embodiments, the prioritization of the patient-specific functional parameters for each of the plurality of patient-specific functional parameters may be based at least in part on at least one target threshold associated with at least one surgeon-specific preference, at least one patient-specific joint deformation metric, at least one patient-specific soft tissue imbalance metric, or any combination thereof.

[0142] In some embodiments, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, may output a plurality of weights according to an error penalty function that minimizes deviation from a target threshold and a plurality of patient-specific functional parameters.

[0143] In some embodiments, the target threshold may include at least one of at least one implant alignment error value for at least one implant alignment function parameter, at least one implant size error value for at least one implant size function parameter, at least one joint laxity error value for at least one joint laxity function parameter, or at least one implant resection thickness error value for at least one implant resection thickness function parameter.

[0144] In some embodiments, the plurality of intraoperative patient-specific data values ​​may include at least one of at least one tracking data of a first bone member, a second bone member, or both, at least one first loosening measurement based on a gap distance between the first bone member and the second bone member, at least one second loosening measurement based on a differential gap between the first bone member and the second bone member, or at least one real-time surgeon-based modification to at least one surgical parameter during the surgical procedure via a graphical user interface of the surgeon support device.

[0145] In some embodiments, the method may further include controlling at least one robotic tool to automatically perform the surgical procedure based on the patient-specific intraoperative surgical plan.

[0146] In some embodiments, the method may further include generating patient-specific post-operative data sets for the patient and a plurality of other patients for retraining at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both.

[0147] In some embodiments, the method may further include generating patient-specific post-operative data sets for the patient and a plurality of other patients for retraining the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both at predefined time intervals.

[0148] In some embodiments, the patient-specific post-operative data set may include post-operative patient outcome data, post-operative implant performance data, and / or post-operative surgeon feedback data regarding the surgical procedure.

[0149] In some embodiments, the weights assigned to the patient-specific functional parameters may be dynamically adjusted during the surgical procedure based on real-time intraoperative data.

[0150] In some embodiments, at least one weight-based implant algorithm can prioritize functional parameters by ranking areas of interest in order of importance based on surgeon-specific preferences and patient-specific needs.

[0151] In some embodiments, the joint can be a knee joint.

[0152] In some embodiments, the surgical procedure may be, for example, a knee replacement, such as a total knee arthroplasty (TKA).

[0153] In some embodiments, the surgical procedure (not limited to a knee surgical procedure) may incorporate at least one type of joint alignment procedure, and the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both may output a plurality of weights based at least in part on the at least one type of joint alignment procedure.

[0154] In some embodiments, the at least one type of joint alignment procedure is based on at least one of mechanical alignment, anatomical alignment, kinematic alignment, restricted kinematic alignment, inverse kinematic alignment, or functional alignment.

[0155] In some embodiments, if the at least one type of joint alignment procedure is mechanical alignment, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both may output at least one implant alignment weight having the highest weight.

[0156] In some embodiments, if at least one type of joint alignment procedure is functional alignment, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, output at least one joint laxity weight with the highest weight.

[0157] In some embodiments, if at least one type of joint alignment procedure is kinematic alignment, the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, output at least one implant resection thickness weight having the highest weight.

[0158] In some embodiments, the patient-specific intraoperative surgical plan may be updated by calculating an error function that incorporates multiple weights and the deviation of the functional parameters from the target threshold.

[0159] In some embodiments, at least one weight-based implant algorithm may assign weights to multiple patient-specific functional parameters using a machine learning model trained based on past surgical data and post-operative outcomes.

[0160] In some embodiments, the plurality of intraoperative patient-specific data values ​​may include at least one real-time soft tissue tension measurement obtained using a distractor.

[0161] In some embodiments, the patient-specific intraoperative surgical plan may be displayed on a wearable augmented reality device worn by the surgeon during the surgical procedure.

[0162] In some embodiments, the patient-specific intraoperative surgical plan may be displayed on the display of the surgical support device during the surgical procedure.

[0163] In some embodiments, the at least one weight-based implant algorithm may assign higher weights to functional parameters associated with regions of interest that exhibit lower error penalties during the surgical procedure.

[0164] In some embodiments, the patient-specific intraoperative surgical plan may include at least one recommendation to balance soft tissue tension by adjusting surgical cutting parameters of the first bone member and the second bone member.

[0165] In some embodiments, the method may include assessing a surgeon performing a surgical procedure as an expert surgeon based on a number of previous surgical procedures performed by the surgeon being equal to or greater than a predefined threshold. The at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, may output a plurality of weights after being trained with surgeon-specific data associated with the expert surgeon.

[0166] In some embodiments, the method may include assessing a surgeon performing a surgical procedure as an expert surgeon based on a number of previous surgical procedures performed by the surgeon being equal to or greater than a predefined threshold. The at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, may output a plurality of weights after being trained with surgeon-specific data associated with the expert surgeon.

[0167] In some embodiments, the method may include generating at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, that outputs a plurality of weights based at least in part on surgeon-specific data stored in an expert surgeon database.

[0168] Publications cited throughout this specification are incorporated herein by reference in their entirety. While one or more embodiments of the present disclosure have been described, it is understood that these embodiments are exemplary only and not limiting, and that many modifications may be apparent to those skilled in the art, including that the various embodiments of the inventive methodologies, inventive systems / platforms, and inventive apparatus described herein may be utilized in any combination with one another. Furthermore, the various steps may be performed in any desired order (and any desired steps may be added and / or deleted).

Claims

1. obtaining a plurality of patient-specific data values ​​prior to implantation of at least one implant into a joint of the patient including a first bone member and a second bone member; inputting a plurality of patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, which outputs a plurality of weights assigned to a plurality of patient-specific functional parameters that facilitate prioritizing the patient-specific functional parameters relative to the plurality of patient-specific functional parameters; utilizing a surgical planning model based at least in part on the plurality of patient-specific data values, the plurality of patient-specific functional parameters, and the plurality of weights to obtain a patient-specific intraoperative surgical plan for implantation of the at least one implant, the patient-specific intraoperative surgical plan including at least one surgical parameter based on the patient-specific functional parameter prioritization; initiating the surgical procedure for transplantation based on the patient-specific intraoperative surgical plan; inputting a plurality of intraoperative patient-specific data values ​​into at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both during the surgical procedure to generate a plurality of updated weights for a plurality of patient-specific functional parameters and updated patient-specific functional parameter prioritizations; inputting the plurality of updated weights, the plurality of intraoperative patient-specific data values, and the updated patient-specific functional parameter prioritization into a surgical planning model during the surgical procedure to obtain an updated patient-specific intraoperative surgical plan having at least one updated surgical parameter; preparing the first bone member, the second bone member, or both during the surgical procedure based on the updated patient-specific intraoperative surgical plan to complete implantation of at least one implant; A method comprising:

2. The plurality of weights may be: at least one implant alignment weight for at least one implant alignment functional parameter of said plurality of patient-specific functional parameters; at least one implant size weight for at least one implant size functional parameter of said plurality of patient-specific functional parameters; at least one joint laxity weight for at least one joint laxity functional parameter of said plurality of patient-specific functional parameters; at least one implant resection thickness weight for at least one implant resection thickness functional parameter of said plurality of patient-specific functional parameters; or any combination thereof, The method of claim 1 , comprising at least one of:

3. The at least one surgical parameter is: at least one surgical cutting parameter for the first bone member; at least one surgical cutting parameter for the second bone member; at least one implant alignment parameter; at least one implant size parameter; at least one joint laxity parameter; or any combination thereof, The method of claim 1 , wherein the at least one of

4. The method of claim 1 , wherein the plurality of patient-specific data values ​​comprises data from a plurality of patient-specific inputs, a plurality of surgeon-specific inputs, a plurality of practice-specific inputs, or any combination thereof.

5. The patient-specific functional parameter prioritization for each of the plurality of patient-specific functional parameters comprises: At least one surgeon-specific preference; at least one patient-specific joint deformity metric; At least one patient-specific soft tissue imbalance metric; or any combination thereof, based at least in part on at least one target threshold associated with The method of claim 1.

6. The at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, outputting the plurality of weights according to an error penalty function that minimizes deviations from a target threshold and the plurality of patient-specific functional parameters; The method of claim 1.

7. The target threshold is: at least one implant alignment error value for at least one implant alignment function parameter; at least one implant size error value for at least one implant size function parameter; at least one joint laxity error value for at least one joint laxity function parameter; or at least one implant resection thickness error value for at least one implant resection thickness functional parameter; The method of claim 6 , comprising at least one of:

8. the plurality of intraoperative patient-specific data values ​​comprising: tracking data of at least one of the first bone member, the second bone member, or both; at least one first laxity measurement based on a gap distance between the first bone member and the second bone member; at least one second laxity measurement based on a differential gap between the first bone member and the second bone member; or at least one real-time surgeon-based modification to the at least one surgical parameter during the surgical procedure via a graphical user interface of a surgeon support device; The method of claim 1 , comprising at least one of:

9. The method of claim 1 , further comprising controlling at least one robotic tool to automatically perform the surgical procedure based on the patient-specific intraoperative surgical plan.

10. 10. The method of claim 1, further comprising generating patient-specific post-operative data sets for the patient and a plurality of other patients for retraining the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both.

11. The method of claim 10 , wherein the patient-specific post-operative data set comprises post-operative patient outcome data, post-operative implant performance data, or post-operative surgeon feedback data regarding the surgical procedure.

12. 10. The method of claim 1, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both prioritize functional parameters by ranking the plurality of patient-specific functional parameters in order of importance based on surgeon-specific preferences and patient-specific needs.

13. the joint is a knee joint, the surgical procedure is a total knee replacement incorporating at least one type of joint alignment procedure; 10. The method of claim 1, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, output the plurality of weights based at least in part on at least one type of joint alignment procedure.

14. The at least one joint alignment procedure includes: Mechanical alignment, anatomical alignment, kinematic alignment, Limited kinematic alignment, Inverse kinematic alignment, or based on at least one of the functional alignments, The method of claim 13.

15. at least one type of joint alignment procedure is a mechanical alignment; 14. The method of claim 13, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both output at least one implant alignment weight having a highest weight.

16. at least one type of joint alignment procedure is a functional alignment; 14. The method of claim 13, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, output at least one joint laxity weight having a highest weight.

17. the at least one type of joint alignment procedure is a kinematic alignment; 14. The method of claim 13, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, output at least one implant resection thickness weight having a highest weight.

18. The method of claim 1 , wherein the patient-specific intraoperative surgical plan is updated by calculating a global error function incorporating the plurality of weights and deviations of the functional parameters from target thresholds.

19. 10. The method of claim 1, wherein the at least one weight-based implant algorithm assigns weights to the plurality of patient-specific functional parameters using a machine learning model trained based on past surgical data and post-operative outcomes.

20. The method of claim 1 , wherein the plurality of intraoperative patient-specific data values ​​includes at least one real-time soft tissue tension measurement obtained using a distractor.

21. The method of claim 1 , wherein the patient-specific intraoperative surgical plan is displayed on a wearable augmented reality device worn by a surgeon during the surgical procedure.

22. The method of claim 1 , wherein the patient-specific intraoperative surgical plan is displayed on a display of a surgical support device during the surgical procedure.

23. The method of claim 1 , wherein the at least one weight-based implant algorithm assigns higher weights to functional parameters associated with regions of interest that exhibit lower error penalties during the surgical procedure.

24. 10. The method of claim 1, wherein the patient-specific intraoperative surgical plan includes at least one recommendation to balance soft tissue tension by adjusting surgical cutting parameters of a first bone member and a second bone member.

25. further comprising assessing the surgeon performing the surgical procedure as an expert surgeon based on a number of previous surgical procedures performed by the surgeon being equal to or greater than a predefined threshold; 10. The method of claim 1, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, are trained using surgeon-specific data associated with expert surgeons before outputting the plurality of weights.

26. assessing the surgeon performing the surgical procedure as a junior surgeon based on the number of previous surgical procedures performed by the surgeon being less than a predefined threshold; 10. The method of claim 1, wherein the at least one weight-based implant algorithm, the at least one weight-based implant machine learning model, or both, output a plurality of weights after training with surgeon-specific data from a generalized model based on surgical workflow associations and a plurality of patient-specific data values.

27. 10. The method of claim 1, further comprising generating at least one weight-based implant algorithm, at least one weight-based implant machine learning model, or both, that outputs a plurality of weights based at least in part on surgeon-specific data stored in an expert surgeon database.

Images