Implant fit analysis

Abstract

Disclosed are a system and method for intraoperative implant fit analysis and life prediction of a prosthetic implant, wherein the prosthetic implant is to be integrated with the patient's physiological tissue, the method comprising the following steps: collecting data through multiple sensors located near the tissue and the implant and through multiple data sources; determining the state and morphology of the tissue and the implant based on the collected data; generating compatibility information between the tissue and the implant based on the determined state and morphology of the tissue and the implant; processing the compatibility information into a form suitable for evaluation against a predetermined comparator; generating means for predicting postoperative implant performance and life using the comparison information and a historical data set of postoperative results; and generating and providing correction information for changing the state and morphology of the tissue to improve postoperative implant performance and life.

Description

Field of the Invention

[0001] The present invention relates to systems and methods for surgical bioimplantation, and more particularly to orthopedic hardware systems for use during surgical procedures such as total knee replacement, total hip replacement, or hip resurfacing procedures.

[0002] The present invention has been developed primarily for use in methods and systems for quality analysis of implantation processes and life expectancy of orthopedic implants in an intraoperative environment and will be described hereinafter with reference to this application. However, it will be appreciated that the invention is not limited to this particular field of use. Background Art

[0003] Any discussion of the background art throughout this specification should in no way be taken as an admission that such background art is prior art, or that such background art is widely known or forms part of the common general knowledge in the field in Australia or worldwide.

[0004] All references cited in this specification (including any patents or patent applications) are incorporated herein by reference. No admission is made that any reference constitutes prior art. The discussion of the references states what their authors claim, and the applicant reserves the right to question the accuracy and relevance of the references. It should be clearly understood that although a number of prior art publications are cited herein, this citation does not constitute an admission that any of these documents constitutes part of the common general knowledge in the art in Australia or any other country.

[0005] Understanding the quality and specifications of an implant allows for various changes and precautions to be taken during surgery. This can provide numerous benefits to the patient, including extending the lifespan or longevity of the implant and improving its success and recovery rates.

[0006] This is particularly evident in surgical procedures involving the musculoskeletal system, such as the knee or hip, where the implant is typically exposed to a great deal of stress. Any medical error made during the implant process can exacerbate or negatively react to this stress, which can result in physical impacts on body movement, potentially causing a degree of pain for the patient. Joint tissues such as cartilage, muscle, and bone comprise the joints within this system that allow it to function, with the performance of the joints naturally degrading as they work. By replacing a certain amount of this degenerated tissue with a prosthetic implant, some degree of lost performance can be restored.

[0007] Total knee arthroplasty is an important form of orthopedic surgery in which a predetermined amount of hard tissue must be removed from the bones involved in the knee joint using an osteotomy. A prosthetic implant is then fixed to the remaining bone to replace the removed hard tissue. This surgical procedure is often required when joint tissue (such as the cartilage around the femur, tibia, and kneecap) begins to wear away. This causes the bones of the patient's affected joint to rub against each other during normal movement and to be subjected to increased levels of stress that would normally be absorbed by the cartilage. By inserting a prosthetic implant into these bones, which is designed to absorb stress in place of the patient's original bone, the painful effects of deteriorating joint tissue can be significantly reduced.

[0008] According to the National Center for Health Statistics, more than 700,000 total knee arthroplasty procedures are performed annually in the United States alone, a number projected to rise to 3.48 million by 2030. These surgeries are overwhelmingly successful initially, with patients, at an average age of 66.2, reporting significant pain reduction and increased mobility. However, after a period of time, issues may arise that require revision total knee surgery. Currently, approximately 8% of all knee replacements require such revision surgery, and by 2030, the annual total number of revisions is expected to increase to match the number of procedures performed annually.

[0009] Total knee revision surgery involves removing the pre-existing implant from the affected joint and replacing it with a new one. This type of surgery is generally considered more complex than a complete arthroplasty (for example, a knee or hip arthroplasty). This is partly because the implant may be well-fixed and bone loss may occur during its removal.

[0010] Prosthetic implants can be fixed to the joint hard tissue using one of two different methods. The first is by attaching the prosthetic implant directly to the hard tissue (a "press fit") and relying on osseointegration, which is the natural growth of hard tissue into / onto the prosthetic implant and stabilizing it. The second method is to form a strong bond between the prosthetic implant and the hard tissue using a fixative such as bone glue. When the implant needs to be removed, the natural bone growth or the inserted fixative and any other joint tissue that is an impediment to removal must be destroyed.

[0011] Multiple osteotomies can then be used to shape the remaining tissue, including hard tissue such as bone, to create a size that matches the new prosthetic implant. However, for subsequent arthroplasty surgeries, depending on the amount of hard tissue lost in the process of removing the previous implant, the amount of hard tissue remaining may not be sufficient for further tissue shaping processes. In such cases, a bone graft may be required, which is the extraction of hard tissue from a different body area of ​​the patient and transplantation of it to the implant area. This requires preoperative planning, specialized equipment, and improved surgical skills. The longevity and overall satisfaction of revision surgery are not as good as the initial replacement surgery, and there is usually a significantly increased risk of complications and harmful problems.

[0012] Regarding total knee arthroplasty surgery, the need for revision total knee surgery is the result of one or more different reasons. These reasons include aseptic loosening, infection, polyethylene wear, instability, pain, osteolysis, and malposition, which account for 23.1%, 18.4%, 18.1%, 17.7%, 9.3%, 4.5%, and 2.9% of all revisions, respectively. These reasons are interdependent; the onset of one reason may be triggered or caused by the initiation of another.

[0013] Aseptic loosening is the biggest cause of revision surgery and refers to the failure of fixation at the interface between the implant and the joint tissue, leading to increased pain levels and joint instability for the patient. The causes of aseptic loosening include four main causes. One such cause is a biological response to wear particles released from the prosthetic implant during use. If enough stress is applied, it may happen that small particles in the critical range of 0.3 to 10 microns can break away from the implant. Depending on the health of the joint tissue and the patient's genetics, this can then lead to a macrophage-based inflammatory response, resulting in osteolysis.

[0014] Another cause of aseptic loosening may be the accumulation of fluid pressure within the joint. This is the result of an overproduction of synovial fluid due to exposed hard tissue or wear particles surrounding the joint. This excess synovial fluid creates additional pressure, which can lead to abnormal bone perfusion or local ischemia, resulting in necrosis and osteolysis.

[0015] Another cause of aseptic loosening may be the physical design of the implant, where the pattern and contour of the surface influence the rate and potential for osseointegration. If this influence is negative, the amount of ingrowth may not be sufficient to stabilize and secure the prosthesis.

[0016] Another cause of aseptic loosening may be the patient's individual biology, including patient-specific characteristics such as age and habits, any pre-existing infections or diseases that may affect the joint, and the patient's genetics. The patient's risk is increased if they participate in regular physical exercise (such as running) or if their joints are naturally fragile.

[0017] Once aseptic loosening due to any one or more of the above causes begins, problems such as infection and malposition, combined with continued loosening of the joint prosthesis, can worsen, pushing the patient further toward revision surgery.

[0018] These reasons can be attributed to prosthesis compatibility, which is defined as the correlation between the state and morphology of the implant and the underlying joint tissue.

[0019] Status determines the extent to which the implant and joint tissue can coexist with each other, indicating the likelihood of problems occurring immediately or postoperatively. The implant material and the health of the tissue generally determine proper fixation.

[0020] Morphology determines the extent to which an implant will physically attach to tissue and influence that tissue and its morphology. If the implant or tissue have different connecting surfaces or morphologies, the contact distribution between them may be irregular or minimal, leading to potential postoperative problems. This can also occur when the implant itself or the connecting shape of the implant receiving site changes due to the stress caused by the implant's insertion, rendering a once compatible morphology no longer compatible.

[0021] The importance of compatibility and the risk of revision are further increased by the patient's physiological status. If the patient is young or maintains an active lifestyle that places constant stress on the implant, this can potentially create new problems while exacerbating existing ones.

[0022] This means that the quality and longevity of an implant therapy is at least partially determined by the condition and morphology of the connected components at the time of implant surgery, and how well these properties allow them to physically fit together. If these properties are poor, the risk of revision due to the aforementioned issues is relatively high, whereas if these properties are less poor, this is often not the case, or the likelihood of revision is significantly reduced. The skill and precision required for this therapy is likely the greatest source of variation in quality, and is generally determined by the experience and competence of the surgeon performing the procedure.

[0023] Common ways to measure the quality of implant therapy generally involve reliance on existing instrumentation or manual observation. Existing instrumentation typically defines the required hard tissue morphology and different osteotomies based on a fixed set of possible options required to achieve it. This works under the assumption that after the osteotomy has been performed, the remaining hard tissue will be a perfect fit for the implant.

[0024] Most of the metrics used to define these osteotomies are calculated based on the inherent properties that a specific set of hard tissues may have, such as the mechanical axis of the knee joint. This means that these metrics rely on the accuracy of these inherent properties and the assumption that the structure of all relevant hard tissues will be identical or very comparable. However, given the variability in hard tissues between different patients, this reliance may not necessarily lead to accurate results.

[0025] Instrument measurements are also typically performed independently of the actual treatment. While they provide quantification of measurable properties, they cannot, by themselves, ensure that the treatment was successfully completed. This means that inconsistencies, such as how straight a particular incision is or how well the instrument can be aligned and positioned, can further impact its accuracy. Consequently, it's not uncommon for the final hard tissue morphology to exhibit various imperfections.

[0026] Surgeons or other surgical personnel typically use manual observation techniques to judge whether an implant fits properly or whether additional modifications are needed. This judgment is built over time based on experience with intraoperative stimulation and feedback. This can include the resistance felt when the implant is inserted, the visible area that is not in contact with the inserted implant, and the range of movement and freedom provided by the implant when manipulating the implant. Because most of these observations are subjective, cannot be verified, and depend heavily on the personnel involved, the overall contribution of these observations to implant therapy is difficult to discern and may not be positive.

[0027] The invention disclosed herein provides a method of performing implant fit analysis and life prediction. Summary of the Invention

[0028] It is an object of the present invention to overcome or ameliorate at least one or more of the disadvantages of the prior art, or to provide a useful alternative.

[0029] One embodiment provides a computer program product for performing the method as described herein.

[0030] One embodiment provides a non-transferable carrier medium for carrying computer executable code, which, when executed on a processor, causes the processor to perform the method described herein.

[0031] One embodiment provides a system configured to perform the methods described herein.

[0032] The present invention provides systems and methods for implant fit analysis and life prediction. In particular, the present invention provides methods for collecting data from different sensors, processing and subsequent interpretation of the data, and generating compatibility information based on the results.

[0033] In one aspect, the present invention provides a system for collecting different types of data based on a data generation method, which can describe various attributes related to the compatibility and immediate fit quality between an implant and a specific hard tissue. The preferred system includes a plurality of different sensors and possible capture tools in a common surgical environment, wherein the sensors operate together in an automated manner to assist the surgeon.

[0034] The selection of sensor comprises at least one sensor that can exist independently or exist as a part of sensor system or sensor group.Each sensor can operate to monitor, sense and collect data about various attributes, characteristics, events or measurement results from the different angles, positions, proximity, layout or arrangement that exist together with its object, exist in its object or pointed to by its object, and this object can be the joint between joint tissue, implant, tissue and implant, surrounding environment, effect or interaction result, independent system or device or the set of system or device and any other favorable source or a series of source sequence.Sensor can be completely self-sufficient, or can need additional device, service, platform or condition just can be suitably interfaced, configured or operated.For example, some sensor may need the device that can form controlled lighting conditions, for example LED lamp.Similarly, motion platform or other manipulable attachment that can move or reposition sensor may also be needed.

[0035] The selected sensors may include sensors based on Raman spectroscopy, spectral imaging, hyperspectral imaging, optical imaging, thermal imaging, fluorescence spectroscopy, microscopy, acoustics, 3D metrology, optical coherence tomography, position, motion, balance, laser power, and any other single, combined, or sequential sensing modality.

[0036] The sensed attributes include the state or morphology of the tissue or implant. State attributes may include composition, hydration, density, necrosis, staining, reflectivity, thermal consistency, deterioration, particle dissolution, and any other single, combined, or sequential state descriptors. Morphological attributes may include shape, flatness, parallelism, roughness, waviness, peak distribution, porosity, stiffness, and any other single, combined, or sequential morphological descriptors.

[0037] In one embodiment, sensing can occur during a surgical procedure. This sensing process can be paused, omitted, or otherwise disregarded in the event of any obstruction that causes a change in the feasible sensing conditions, such as a person obstructing the sensor, excessive light or noise, untimely movement of an object, or any other adverse sensing condition, alone, in combination, or in sequence.

[0038] In another embodiment, sensing can interrupt the natural course of the surgical procedure for a predetermined or intraoperatively determined duration to provide an environment conducive to the sensing procedure. Such interruption can include a change in the surgical environment, which can include temporary evacuation of personnel, alteration or dimming of lighting conditions, changes in atmosphere, repositioning of the subject, or any other single, combined, or sequential environmental changes.

[0039] In one embodiment, the sensory data may be interpreted based on the single sensor providing the sensory data, independent of other sensors that may be operating around or in association with the sensor.

[0040] In another embodiment, the sensory data may be interpreted based on a system, sensor group, or multiple sensor groups, where the content in the sensory data may be consistent or defined by attributes, similarities, conditions, states, or any other single, combined, or sequential grouping factors.

[0041] In another embodiment, sensed data interpreted based on a collection of sensors may be summarized to provide increasingly accurate information, used as a measure of fault tolerance for determining operating efficiency, or used in any other single, combined, or sequential manner in which the coordinated operation of the sensors involved may be beneficial.

[0042] In further embodiments, sensed data originating from a single system, a single sensor group, or multiple sensor groups can be interpreted independently of or in relation to ambient or internal conditions and physical sensor arrangements, which may include temperature, humidity, pressure, varying amounts of lighting and their directions, different positions, angles, nearby areas, or layouts, or any other single, combined, or sequential influencing factors.

[0043] In another aspect, the present invention provides methods for processing sensory data into at least one different sequential form that increases its usability or evaluability. Preferred methods include cleaning the data to remove noise or redundancy, changing the format or arrangement of the data, sampling the data to separate it into multiple parts or regions that may be considered useful, normalizing the data to limit it to a comparable range, decomposing the data to define its component elements, or aggregating the component elements into entities with significant utility.

[0044] The sensed data provided by any particular selected sensors will depend on those sensors and may include specific wavelengths, signals, arbitrary quantities, equations, coordinates, models, or any other single, combined, or sequential form of data that can be interpreted directly or indirectly.

[0045] The processing of sensory data can involve a variety of different, similar, or identical methods performed in the same or alternating order to produce a single or multiple subsequent forms that lead to a final form. Certain algorithms or methods may not be suitable for all forms of data or sensor types, but this can be changed by making appropriate modifications to the algorithms or methods. Each individual form can contribute beneficially to subsequent forms and is not necessarily included in the final form.

[0046] The constituent elements represent the independent component or the summary component existing in the raw data.The quantity and type of the constituent elements produced depend on the data form, any previously executed processing method, the situation or environment in which sensing occurs or may cause any other single, combined or sequential conditions that have multiple components in the data.The constituent elements of joint tissue commonly include cancellous bone, cortical bone, cartilage, fat, ligament, muscle, capsule or meniscus.Extra constituent elements can exist as the specialized attributes of these constituent elements, which can include composition, degree of hydration, density, necrosis, reflectivity, temperature or any other single, combined or sequential element that may describe the state of joint tissue.

[0047] In one embodiment, a significant portion of data or data sets may be removed that may not significantly impact the conclusions drawn from the remaining data or that are incorrect or erroneous. This may include data in which the event of interest or aspects that may support the event of interest do not occur, data consisting of unstable values, or any other single, combined, or sequential states from which extraction of usefulness is impractical or negligible.

[0048] In another embodiment, data sets or data series corresponding to the same, similar, or different events with structural similarities may be averaged or otherwise combined to summarize portions or regions where variation, including noise or erroneous data, may exist, which may then be removed from a single or combined data set or data series.

[0049] In another embodiment, similar data with smaller values ​​may be summarized or combined into a single or multiple representative data sets to reduce the absolute amount of data without significantly affecting any derived conclusions.

[0050] In one embodiment, the format, form, or structure of the data may be rearranged, altered, or changed to produce additional or alternative utility by methods that may include flattening the data or changing the position or relationship between specific values ​​or ordered values.

[0051] In one embodiment, the data may be sampled to extract regions or portions deemed more favorable, or to create a series or set of data samples that may be processed or manipulated separately for purposes such as cross-validation or testing.

[0052] In one embodiment, the data may be normalized by algorithms and methods such as constant shift, smoothing, scaling, standard normal variation factor, baseline correction, continuum removal, or any other single, combined, or sequential algorithm or method that can improve data consistency.

[0053] In one embodiment, the data may be decomposed or deconvolved into its constituent elements or features, which may be accomplished through algorithms and methods including an automatic object generation process, pixel purity index, N-FINDR, independent component analysis, nonlinear least squares, fuzzy k-means, or any other single, combined, or sequential algorithms and methods capable of achieving decomposition. Depending on the form of the data provided and its purpose, some of these algorithms and methods may not be feasible without potential modifications.

[0054] In another embodiment, the constituent elements may be identified before extracting them to determine the constituent elements present in the data and any indications that may assist in their extraction.

[0055] In another embodiment, sequences of constituent elements or sets of constituent elements may be averaged or combined in a beneficial manner, as long as they share or do not share any similar patterns or other elements that can be used as a grouping means. This may occur when the number of constituent elements is greater than the expected number.

[0056] In further embodiments, decomposition may include removing dimensions of the data to reduce complexity or computational load. This may be performed using algorithms and methods including decision trees, random forests, high correlation filtering, backward feature elimination, factor analysis, principal component analysis, linear discriminant analysis, generalized discriminant analysis, or any other single, combined, or sequential algorithms and methods capable of removing dimensions.

[0057] In one embodiment, representative, constituent, or otherwise individual collections of data, elements, or features may be aggregated together into a single entity or a smaller number of entities that may be more easily processed while maintaining similar or increased utility.

[0058] In another aspect, the present invention provides methods for interpreting processed data into at least one different subsequent form that can improve its usefulness. Preferred methods include calculating customized or standardized mathematical or statistical measures, provided by external parties or internal controllers, and training and executing machine learning, data science, and mathematical algorithms and methods.

[0059] Interpretation of processed data can involve executing various different, similar, or identical methods in the same or alternating order to produce a single or multiple subsequent forms that lead to the final form. Certain algorithms and methods may not be suitable for all forms of data or sensor types, but this can be changed by making appropriate modifications to the algorithms and methods. Each individual form can contribute beneficially to subsequent transformations without necessarily being included in the final form.

[0060] In one embodiment, measurements defined by mathematical or statistical equations, theories, or concepts (such as mean, standard deviation, and variance) may be calculated to gain insights into summary information based on the processed data.

[0061] In another embodiment, measurements defined by standards bodies such as the International Standards Organization (ISO), or customized to a specific subject matter or environment associated with the processed data, can be calculated to gain insights into specific properties or characteristics such as surface flatness and roughness.

[0062] In one embodiment, prior medical records or history directly or indirectly related to a particular patient may be provided.

[0063] In another embodiment, explicit information related to an implant or other fixed or manufactured entity may be provided directly by the company responsible for its production or manufacture.

[0064] In another embodiment, pre-operative scans, studies, or preliminary procedures may be provided for the purpose of developing further information related to a particular issue or question.

[0065] In further embodiments, trained medical personnel or other personnel with verifiable capabilities may directly or indirectly provide observations or default conclusions surrounding or relating to the subject based on currently accessible and prior knowledge.

[0066] In one embodiment, a control unit responsible for managing a particular sensor or set of sensors may provide analysis results based on the data collected and processed internally.

[0067] In one embodiment, the processed data may require additional processing or manipulation before being provided to one or more machine learning, data science, or mathematical algorithms and methods.

[0068] In another embodiment, a single processed data or processed data set may be used to train a single or multiple machine learning, data science, or mathematical algorithms and methods.

[0069] In further embodiments, the processed data may be provided to a single or a set of trained machine learning, data science, or mathematical algorithms and methods to produce corresponding outputs.

[0070] In another aspect, the present invention provides methods for generating compatibility information based on interpreted data of tissues, associated prosthetic implants, and the joints therebetween. Preferred methods include generating a degree of compatibility, analyzing the effects of implant insertion or fixation, assessing implant fit, and predicting the life and performance of the implant.

[0071] The generation of compatibility information can involve various different, similar, or identical methods executed in the same or alternating order to produce a single or multiple subsequent forms leading to the final form. Certain algorithms or methods may not be suitable for all forms of data or sensor types, but this can be changed by making appropriate modifications to the algorithms or methods. Each individual form can contribute beneficially to subsequent transformations without necessarily being included in the final form.

[0072] Compatibility information includes any analysis or conclusion that can describe the quality of the bond between a particular tissue and an associated implant before, shortly after, and for a period of time after implantation. This includes how the state or biological characteristics of the tissue and implant affect each other, the physical connectivity of the two in terms of their morphology, insertion accuracy, and the longevity of the bond when these factors, as well as the habits of the individual undergoing the procedure, are taken into account.

[0073] The bond between a prosthetic implant and tissue can rely on bone ingrowth through a process known as osseointegration, or it can be artificially established using fixatives such as bone cement.

[0074] In one embodiment, the health of the tissue and the patient may be considered to determine the likelihood of fixation and subsequent viability of a connected joint.

[0075] In one embodiment, the materials comprising the prosthetic implant can be compared to the tissue status and any required fixatives to determine if any adverse reactions may occur, both intraoperatively and postoperatively.

[0076] In another embodiment, the patient's lifestyle, including their level of activity and daily routine, may be considered to determine the stresses to which the prosthetic implant and connected joints may be subjected.

[0077] In one embodiment, the shape and form of the implant can be compared to the shape and form of the tissue to determine the likelihood and difficulty of insertion.

[0078] In another embodiment, the extent and distribution of contact that an implant will make with tissue upon insertion can be determined to gauge the likelihood of fixation and longevity of the connected joint.

[0079] In one embodiment, any surface disruption, density reduction, or other impact on the tissue or implant upon insertion may be determined to inform other measurements and comparisons so that compatibility information may be adjusted accordingly.

[0080] In another embodiment, the spread or dislocation of any fixative applied to the implant or tissue upon insertion may be determined to ensure that sufficient distribution is maintained which may allow for proper fixation.

[0081] In one embodiment, an ideal fit of the implant to the tissue may be calculated and compared to the actual fit of the implant to the tissue to determine the amount of deviation.

[0082] In another embodiment, positional changes and rotations may be applied to the inserted implant to improve the quality of the implant and produce less deviation when compared to the calculated ideal fit.

[0083] In one embodiment, the generated compatibility and verified implant life and performance data can be used to train machine learning, data science, or mathematical algorithms and methods.

[0084] In another embodiment, verified implant life and performance data can be retrieved from previously approved patients who had the implant under specific conditions for a set period of time.

[0085] In another embodiment, machine learning, data science, and mathematical algorithms or methods can be based on supervised approaches. These algorithms or methods can include linear and polynomial regression, logistic regression, naive Bayesian networks, Bayesian networks, support vector machines, decision trees, random forests, k-nearest neighbor classifiers, neural networks, and any other single, combined, or sequential supervised approaches.

[0086] In one embodiment, it may be necessary to process the compatibility data using algorithms and methods to obtain a more evaluable form, which algorithms and methods may include the algorithms and methods set out in the second aspect of the present invention.

[0087] In one embodiment, the validated data pool will be split into at least two parts, where these splits are not necessarily even or proportional.

[0088] In another embodiment, a single split validated data set or split validated data sets may be provided to a single or multiple machine learning, data science, or mathematical algorithms or methods in a sequential, simultaneous, or periodic manner.

[0089] In another embodiment, a single data set or dataset of all or part of the remaining split verified data can be provided to a previously trained single or multiple machine learning, data science, or mathematical algorithms and methods to determine the accuracy of the corresponding output relative to the external confirmation output.

[0090] In another embodiment, the accuracy of a particular trained machine learning, data science, or mathematical algorithm and method may be determined to be adequate based on its statistical significance, which may be influenced by or limited by its application for prediction or estimation.

[0091] In further embodiments, if accuracy proves insufficient, the selected validated data, its input procedures, single or multiple machine learning, data science, or mathematical algorithms and methods, and any other single, combined, or sequential reasons may be modified, removed, rearranged, or added to potentially improve accuracy.

[0092] In one embodiment, the compatibility data may be provided to a single trained machine learning, data science, or mathematical algorithm or method, or a collection thereof, to produce a corresponding output.

[0093] In another embodiment, corresponding outputs from at least two machine learning, data science, or mathematical algorithms or methods may be averaged, combined, or compared to potentially draw increasingly definitive conclusions.

[0094] In one embodiment, simulations can be constructed to test all or a collection of available data under various conditions, which can provide insights into phenomena such as the effects of implant insertion and changes in stress levels applied to connected joints.

[0095] In one embodiment, corrective information for modifying tissue morphology is generated to inform the surgeon about a set of actions needed to improve implant performance and longevity.

[0096] In one embodiment, the correction information samples different possible sets of grouped actions for predicted post-operative implant performance.

[0097] In another embodiment, the correction information includes numerical quantifications of implant performance and longevity for currently existing and subsequently generated tissue morphologies after the proposed set of actions has been performed.

[0098] In another embodiment, the correction information has a pre-configured threshold above which a corrective action may be identified as not feasible given the surgical cutting technique being applied and its inherent inaccuracies.

[0099] Therefore, it is clear that current methods for measuring and ensuring implant quality, although not optimal, are still often used. Therefore, there is a need for improved systems and methods for measuring key parameters of orthopedic therapy and assessing prosthesis viability, as well as systems and methods used by surgeons in orthopedic prosthetic implant therapy to maximize the integration and viability of the prosthesis for long-term patient benefit.

[0100] According to a first aspect of the present invention, a method for intraoperative implant fit analysis and life prediction of a prosthetic implant is provided, wherein the prosthetic implant is to be integrated with the patient's physiological tissue. The method may include the following steps: collecting data through multiple sensors located near the tissue and the implant and through multiple data sources. The method may include the following further steps: determining the state and morphology of the tissue and the implant based on the collected data. The method may include the following further steps: generating compatibility information between the tissue and the implant based on the determined state and morphology of the tissue and the implant. The method may include the following further steps: processing the compatibility information into a form suitable for evaluation against a predetermined comparator. The method may include the following further steps: generating means, which utilizes comparative information and a historical data set of postoperative results to predict postoperative implant performance and life. The method may include the following further steps: generating and providing correction information, which is used to change the state and morphology of the tissue to improve postoperative implant performance and life.

[0101] According to a specific arrangement of the first aspect, a method for intraoperative implant fit analysis and life prediction of a prosthetic implant is provided, wherein the prosthetic implant is to be integrated with the patient's physiological tissue, the method comprising the following steps: collecting data through multiple sensors located near the tissue and the implant and through multiple data sources; determining the state and morphology of the tissue and the implant based on the collected data; generating compatibility information between the tissue and the implant based on the determined state and morphology of the tissue and the implant; processing the compatibility information into a form suitable for evaluation against a predetermined comparator; generating means for predicting postoperative implant performance and life using the comparison information and a historical data set of postoperative results; and generating and providing correction information for changing the state and morphology of the tissue to improve postoperative implant performance and life.

[0102] The tissue may include biological tissue including bone. The prosthetic implant may include a knee prosthesis or a hip prosthesis. The prosthetic implant may include one or more features including threads or patterns on one or more surfaces to promote osseointegration and / or increase the rigidity of fixation to the tissue.

[0103] The sensor may comprise at least one sensor that exists independently or as part of a sensor system or sensor group. The sensor may comprise at least one sensor that is completely self-contained.

[0104] The sensors may include at least one sensor that requires additional devices, services, conditions, platforms, or any other single, combined, or sequential requirements to be properly interfaced, configured, or operated.

[0105] The sensor may include at least one sensor individually configured to monitor, sense, collect and provide data based on various characteristics, features, events or measurements from different angles, positions, proximity, vicinity, motion, speed, layout or arrangement with, within or pointed at by its object.

[0106] The object may include one or more of the tissue, the implant, the connecting joint, the surrounding environment, the result of an action or interaction, a separate system or device or a collection of systems or devices, and any other source or series of sources associated therewith.

[0107] The object may be processed, altered, or adjusted to affect its original, initial, or current state for the purpose of preservation, identification, unification, fixation, or any other single, combined, or sequential goal.

[0108] An object may be modified structurally, chemically, or by any other single, combined, or sequential means that is capable of changing the form of the object as part of or independent of any intraoperative therapy, surgical procedure, or any other single, combined, or sequential medical procedure.

[0109] The sensors may be configured to operate in an automated fashion, by manual triggering, or any combination or sequence of manual and automated triggering.

[0110] Manual triggering may include a manual trigger including a button, voice command, gesture control, or other physical actuation.

[0111] Sensors may be configured to sense indefinitely, periodically, once, or in any other single, combined, or sequential sensing manner as affected by the situation, environment, user control, sensor configuration, and any other single, combined, or sequential changing factors that can have a direct or indirect effect.

[0112] Sensing can be configured to operate in real time, near real time, with some form of delayed processing, or in any other single, combined, or sequential processing manner that can be affected by the situation, environment, user control, sensor configuration, and any other single, combined, or sequential changing factors that can have a direct or indirect effect.

[0113] A sensor may require external intervention to operate properly, including changes in the sensor's position, angle, vicinity, proximity, configuration, lighting, timing, or any other single, combined, or sequential sensor, situation, or environment.

[0114] A data source may include a record, file, database, system, or any other single, combined, or sequential internal or external data source that may have been verified or validated.

[0115] Tissue state can include one or more of composition, hydration, density, necrosis, staining, reflectance, and temperature. Implant state can include one or more of composition, deterioration, density, and particle dissolution. Tissue and implant morphology can include one or more of shape, flatness, parallelism, roughness, waviness, peak distribution, porosity, and stiffness. Determination of tissue and implant state and morphology can include at least one work action related to processing of sensed data.

[0116] Processing of sensory data may include cleansing the data, including removing or repairing any noise, erroneous or redundant data, and any other single, combined or sequential processes adapted to remove negligible data or improve the overall usefulness of the remaining data.

[0117] Processing of the sensed data may include formatting the data, including rearranging the data into a more appropriate structure or form, flattening the data, or extracting the data from its current storage device.

[0118] Processing of sensory data may include sampling the data, including selection or partitioning of a portion of the data.

[0119] Processing of the sensory data may include scaling or alignment of the data so that the values ​​of the data are within a comparable range or achieve some additional level of comparability.

[0120] Processing of sensory data may include decomposition or deconvolution of the data to enable separation of representative or other specific features or portions of the data into constituent elements or elements that alone provide greater utility.

[0121] Processing of sensory data may include aggregation of the data so that separate features, constituent elements, segments, or portions of the data may be combined into a single entity.

[0122] Processing of sensory data may include at least one work action related to any other single, combined or sequential process, operation, generation, modification or any other function that can better prepare the data for use.

[0123] If processing of the sensed data has been performed separately or independently by an additional entity such as a sensor controller or a bridge device, the processing of the sensed data may not be performed or may be partially performed.

[0124] The determination of the state and morphology of the tissue and implant may include at least one work action related to the interpretation of the processed data.

[0125] Interpretation of processed data may include at least one working action related to any general or specific mathematical equation, theory, calculation, concept, or any other single, combined, or sequential mathematical function.

[0126] Interpretation of processed data may include at least one work action associated with the performance of a process or function that calculates a customized or standardized geometric measure, morphological measure, structural measure, or any other single, combined, or sequential related measure.

[0127] Interpretation of the processed data may include at least one work action related to the execution of a machine learning, data science, or mathematical algorithm or method.

[0128] If an additional entity, such as a sensor controller or a bridge device, has separately or independently performed the interpretation of the processed data, the interpretation of the processed data may not be performed or may be partially performed.

[0129] The interpretation of processed data may include at least one work action related to any observation or default conclusion provided by a verified person. The interpretation may be explicitly provided through medical records or history, preoperative therapy, or any other single, combined, or sequential form that can be independent of any generated or processed data. The interpretation of processed data may include at least one work action related to any other single, combined, or sequential process, equation, generation, modification, or any other form of interpretation.

[0130] According to certain aspects and embodiments disclosed herein, compatibility information can be generated based on interpreted data from tissue comprising a receiving surface, an associated implant comprising an engagement surface, and a joint between the tissue and the implant, the joint comprising a contact portion between the receiving surface and the engagement surface, as described in any of the preceding claims. Generating the compatibility information can include the steps of: generating a degree of compatibility of the joint with either or both of the receiving surface and the engagement surface; analyzing the impact of implant insertion or fixation; evaluating implant fit; and predicting the life and performance of the implant.

[0131] Generating the degree of compatibility may include at least one work action related to a comparison of the determined state and morphology of the tissue and implant.

[0132] The determined comparison of the state and morphology of the tissue and implant may include at least one work action associated with determining compatibility of the state of the tissue and implant.

[0133] Determining the compatibility of the tissue and the state of the implant may include determining whether the implant material is suitable for the tissue.

[0134] The appropriateness of the implant material may include the potential for adverse reactions to occur at any time and for any duration, including intraoperatively or postoperatively.

[0135] The suitability of the implant material may include the intended or possible fixation material, substance, process, or any other single, combined, or sequential fixation agents or fixation methods.

[0136] The suitability of the implant material may include possible stresses, pressures, anticipated usage scenarios, and any other single, combined, or sequential events or circumstances to which the implant may be subjected postoperatively.

[0137] Determining the compatibility of the tissue and the state of the implant may include examining the health of the tissue to measure fixation potential and viability.

[0138] The comparison of the determined state and morphology of the tissue and implant may include at least one work action related to determining the compatibility of the morphology of the tissue and implant.

[0139] Determining the compatibility of the tissue and implant morphology may include determining whether the shape and morphology of the tissue will enable insertion of the implant and the attendant difficulties.

[0140] Determining the compatibility of the tissue and implant morphology may include determining the extent to which the implant contacts the tissue upon insertion and the resulting distribution this will produce.

[0141] Determining the compatibility of the morphology of the tissue and the implant may include determining the extent to which the surface of the tissue fills the threads of the implant and the extent to which the distribution pattern of the tissue is comparable within the threads in comparison.

[0142] Analyzing the effects of implant insertion or fixation may include determining the likely effects that inserting the implant will have on the tissue or the implant.

[0143] The effect of inserting the implant on the tissue may include surface disruption, density reduction, or any other single, combined, or sequential surface or state changes.

[0144] Any surface modification capable of affecting the degree of compatibility of at least one other single, combined, or sequential determination is not limited to the process or result of the explicitly stated method or technique.

[0145] The effect of inserting the implant on the tissue may include spreading, distributing, or affecting any single or combined applied fixatives, which can be present directly or indirectly.

[0146] The assessment implant cooperation can comprise that the current layout of this implant is compared with the ideal layout calculated.Layout can be limited by the following factors: the filling of tissue and pattern, the stress distribution on this implant and surface contact in the degree of contact between this tissue and this implant, this implant thread and any other single, combination or sequential qualitative or quantitative measurement, characteristic or feature.Ideal layout can be limited by the beneficial value or the favourable value of the characteristic or feature that are used to describe implant layout.

[0147] The quality of implant fit can be affected by the state and morphology of the implant and tissue, the situation and environment, the intended use scenario and the stresses to which the implant will be subjected, and any other single, combined or sequential qualitative or quantitative measure, characteristic or feature of mechanical or structural forces.

[0148] The results of an assessment may be ambiguous and may provide a quantitative or qualitative measure based on all available information appropriate to allow an informed decision.

[0149] Various suggestions, comments, indicators, prompts, or any other single, combined, or sequential means may be used to inform the entity regarding necessary changes needed to bring the current position closer to the calculated ideal position.

[0150] Additional analysis is performed in the event of repositioning, moving, rotating the implant, or any other single, combined, or sequential change to the implant's current position that results in a change in the degree of compatibility.

[0151] Predicting the life and performance of an implant can include at least one work action that is related to consideration of generated compatibility information, the state and morphology of tissue and implant, fixation method, previous medical history or record, expected usage, implant stress level, and any other single, combined or sequential information suitable to assist or support the prediction.

[0152] The lifespan and performance of an implant may include quantitative measures of time and qualitative measures related to the ease with which certain tasks are performed, as well as any other single, combined, or sequential measures suitable to provide additional insight.

[0153] The generated implant life and performance information can be used directly or can be interpreted to generate recommendations based on the patient's usage or current lifestyle.

[0154] Predicting the life and performance of an implant may include at least one work action related to the execution of a machine learning, data science or mathematical entity, concept, model, equation, or any other single, combined or sequential embodiment.

[0155] At least one simulation or any other computational method or entity may be used to predict, generate, calculate, verify, validate, or any other single, combined, or sequential use adapted to produce information or utility.

[0156] The processing of the compatibility information or data may include at least one work action associated with converting the compatibility information or data into an evaluable form.

[0157] The transformation of data may include at least one work action involving single, multiple, combined or sequential pre-processing steps.

[0158] The method of claim 67, further comprising a pre-processing step, the pre-processing step comprising cleansing the data, including removing or repairing any noise, errors, or redundant data, and any other individual, combined, or sequential processes adapted to improve the usefulness of the remaining data. The pre-processing step may comprise formatting the data, including rearranging the data into a more suitable structure or form, flattening the data, or extracting the data from its current storage device, and any other individual, combined, or sequential formatting adapted to improve the usefulness of the data.

[0159] Pre-processing steps may include sampling of the data, including selection or partitioning of portions of the data, and any other single, combined, or sequential processes adapted to produce more representative or advantageous data.

[0160] The transformation of data may include at least one work action involving single, multiple, combined or sequential raw data operations or processed data operations.

[0161] Manipulation of raw or processed data may include scaling or alignment of the data so that the values ​​of the data are within a comparable range or achieve some additional level of comparability.

[0162] Manipulation of raw or processed data may include decomposition of the data to separate representative or other specific features or portions of the data into constituent elements or elements that provide more utility than when used alone.

[0163] Manipulation of raw or pre-processed data may include aggregating the data to combine separate features, constituent elements, segments, or portions of the data into a single entity.

[0164] The transformation of data may include at least one work action related to any other single, combined or sequential process, operation, generation, modification or any other function adapted to prepare the data for use or evaluation.

[0165] The comparator may include data sets in similar or otherwise comparable form pertaining to single, combined or sequential comparison information.

[0166] After the surgery has occurred for a certain period of time, a postoperative result may be received from the patient. The received postoperative result may undergo at least one working action as described above.

[0167] The means for generating predicted post-operative implant performance may include training a machine learning, data science or mathematical entity, concept, model, equation, or any other single, combined or sequential embodiment configured to provide performance predictions.

[0168] Any machine learning, data science, or mathematical entity, concept, model, equation, or any other single, combined, or sequential embodiment can be augmented by the introduction of new data.

[0169] Generating corrective information for altering the morphology of the tissue and providing the corrective information including a set of actions can be adapted to enable the surgeon to improve the performance and longevity of the implant.

[0170] The correction information may include a sample of a possible set of motions that differ from the expected post-operative implant performance.

[0171] The correction information may include numerical quantification of the implant performance and longevity for currently existing and subsequently generated tissue morphology after the proposed set of actions has been performed.

[0172] This corrective information may include pre-configured thresholds above which corrective action may be identified as infeasible given the surgical cutting technique being applied and its inherent inaccuracies.

[0173] The method of any of the preceding claims, wherein the sensed data, raw data, pre-processed data, manipulated data, processed data, interpreted data, usable data, evaluable data, or any other single, combined, or sequential generated data, derived data, or received data is stored electronically, including offline, online, or a combination of both, for later retrieval, processing, or any other single, combined, or sequential form of use.

[0174] Any at least one working action can be influenced, affected, adjusted, or directed by a patient-specific deformation or problem, which includes one or more of the following: valgus or varus error, mechanical alignment error, or any other error that causes the patient's anatomy to differ from what is considered normal or ideal.

[0175] At least one work action can occur in an intraoperative environment. The at least one work action can occur in the same, different, or alternating order and can be adapted to produce the same, similar, or different end results. The at least one work action can occur in real time, near real time, via a delayed processing procedure, or in any other single, combined, or sequential processing manner.

[0176] The required data processing or data storage may occur internally, externally at a centralized, distributed, or other online entity, or in any other single, combined, or sequential computing manner.

[0177] According to a second aspect of the present invention, a system for supporting surgical bio-implant therapy for integrating a prosthetic device with a patient's tissue is provided. The system may include one or more sensors for sensing characteristics of the patient's tissue morphology to collect at least state and morphology data to generate collected data. The system may further include one or more processors. The one or more processors may be adapted to pre-process and manipulate the collected data to generate processed data having a form suitable for interpretation. The one or more processors may be further adapted to interpret the processed data to extract data representing the structure of the patient's tissue and the prosthetic device. The one or more processors may be further adapted to determine compatibility data between the data representing the patient's tissue and the data representing the prosthetic device to determine the compatibility of the state of the connecting surface of the implant with the receiving surface of the patient's tissue. The one or more processors may be further adapted to use the compatibility data to predict the lifespan and performance of the prosthetic device. The one or more processors may be further adapted to generate correction data for modifying the receiving surface of the patient's tissue to improve the prediction of the lifespan and performance of the prosthetic device.

[0178] According to a specific arrangement of the second aspect, a system for supporting surgical bioimplant therapy for integrating a prosthetic device with a patient's tissue is provided, the system comprising: one or more sensors for sensing characteristics of the patient's tissue morphology to collect at least state and morphological data to generate the collected data; one or more processors adapted to: pre-process and operate the collected data to generate processed data having a form suitable for interpretation; interpret the processed data to extract data representations of the structure of the patient's tissue and the prosthetic device; determine compatibility data between the data representations of the patient's tissue and the data representations of the prosthetic device to determine compatibility of the state of the connecting surface of the implant with the receiving surface of the patient's tissue; use the compatibility data to predict the life and performance of the prosthetic device; and generate correction data for modifying the receiving surface of the patient's tissue to improve the prediction of the life and performance of the prosthetic device.

[0179] The one or more sensors may be selected from the group consisting of a Raman spectroscopy sensor, a spectral imaging sensor, a hyperspectral imaging sensor, an optical imaging sensor, a thermal imaging sensor, a fluorescence spectroscopy sensor, a microscopy sensor, an acoustic sensor, a 3D metrology sensor, an optical coherence tomography sensor, a position sensor, a motion sensor, or a balance sensor.

[0180] The one or more sensors may be adapted to sense properties of the state and / or morphology of the patient's tissue and / or the prosthetic implant.

[0181] The state attributes sensed of the patient's tissue and / or the prosthetic implant can be selected from one or more of the following: composition, hydration, density, necrosis, coloration, reflectance, thermal consistency, deterioration, particle dissolution, and any other single, combined, or sequential state descriptors.

[0182] The morphological properties sensed of the patient's tissue and / or the prosthetic implant can be selected from one or more of the following groups: shape, flatness, parallelism, roughness, waviness, peak distribution, porosity, stiffness, and any other single, combined, or sequential morphological descriptors.

[0183] The system may further include means for outputting predictions of the lifespan and performance of the prosthetic device.

[0184] The system may further include means for outputting the generated correction data for modifying the receiving surface of the patient's tissue to improve prediction of the lifespan and performance of the prosthetic device.

[0185] The collected data may further include historical data including historical surgical procedure record data and / or historical patient data.

[0186] Preprocessing and manipulation of the collected data may include one or more of the following: means for removing noisy, erroneous, or redundant data; means for formatting the data into an appropriate data format; means for sampling the collected data into one or more representative segments; means for scaling or aligning the data; decomposing the data into its constituent elements; and means for aggregating the data to create a statistically significant data structure.

[0187] According to a third aspect of the present invention, there is provided a system for intraoperative implant fit analysis and life prediction of a prosthetic implant to be integrated with a patient's physiological tissue, the system comprising:

[0188] one or more processors;

[0189] a memory coupled to the one or more processors and configured to store instructions that, when executed by the one or more processors, cause the processor to:

[0190] collecting data via a plurality of sensors positioned proximate the tissue and the implant and via a plurality of data sources;

[0191] determining the state and morphology of tissues and implants based on the collected data;

[0192] generating compatibility information between the tissue and the implant based on the determined states and morphologies of the tissue and the implant;

[0193] processing the compatibility information into a form suitable for evaluation against a predetermined comparator;

[0194] generating means for predicting post-operative implant performance and longevity using comparative information and historical datasets of post-operative outcomes; and

[0195] Corrective information is generated and provided that is used to alter the state and morphology of the tissue to improve post-operative implant performance and longevity.

[0196] According to a fourth aspect of the present invention, there is provided a non-transitory computer-readable storage device having instructions stored thereon, the instructions, when executed by a processor, causing the processor to perform operations for intraoperative implant fit analysis and lifespan prediction of a prosthetic implant to be integrated with a patient's physiological tissue, the operations comprising:

[0197] collecting data via a plurality of sensors positioned proximate the tissue and the implant and via a plurality of data sources;

[0198] determining the state and morphology of tissues and implants based on the collected data;

[0199] generating compatibility information between the tissue and the implant based on the determined state and morphology of the tissue and the implant;

[0200] processing the compatibility information into a form suitable for evaluation against a predetermined comparator;

[0201] generating means for predicting post-operative implant performance and longevity using comparative information and historical datasets of post-operative outcomes; and

[0202] Corrective information is generated and provided that is used to alter the state and morphology of the tissue to improve post-operative implant performance and longevity.

[0203] According to a fifth aspect of the present invention, there is provided a computer program element comprising computer program code means for causing a computer to perform a process comprising:

[0204] collecting data via a plurality of sensors positioned proximate the tissue and the implant and via a plurality of data sources;

[0205] determining the state and morphology of tissues and implants based on the collected data;

[0206] generating compatibility information between the tissue and the implant based on the determined state and morphology of the tissue and the implant;

[0207] processing the compatibility information into a form suitable for evaluation against a predetermined comparator;

[0208] generating means for predicting post-operative implant performance and longevity using comparative information and historical datasets of post-operative outcomes; and

[0209] Corrective information is generated and provided that is used to alter the state and morphology of the tissue to improve post-operative implant performance and longevity.

[0210] According to a sixth aspect of the present invention, there is provided a computer-readable medium having a program recorded thereon, wherein the program is configured to cause a computer to execute the following process, the process comprising:

[0211] collecting data via a plurality of sensors positioned proximate the tissue and the implant and via a plurality of data sources;

[0212] determining the state and morphology of tissues and implants based on the collected data;

[0213] generating compatibility information between the tissue and the implant based on the determined state and morphology of the tissue and the implant;

[0214] processing the compatibility information into a form suitable for evaluation against a predetermined comparator;

[0215] generating means for predicting post-operative implant performance and longevity using comparative information and historical datasets of post-operative outcomes; and

[0216] Corrective information is generated and provided that is used to alter the state and morphology of the tissue to improve post-operative implant performance and longevity. BRIEF DESCRIPTION OF THE DRAWINGS

[0217] Regardless of any other forms that may fall within the scope of the invention, one / more preferred embodiments of the present invention will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0218] Figure 1 is a schematic flow chart depicting the implant fit analysis process, including the steps required for a complete implementation of the preferred embodiment;

[0219] Figure 2 is a detailed schematic flow chart depicting the Figure 1 The data sources and related processes involved in the collection and accessibility of the data introduced in the exemplary data collection steps;

[0220] Figure 3 is a detailed schematic flow chart depicting the Figure 1 The processes and operations involved in data preparation introduced in the exemplary data processing steps;

[0221] Figure 4 is a detailed schematic flow chart describing the Figure 1 the algorithms, methods and calculations involved in the analysis of the processed data introduced in the exemplary data interpretation steps of;

[0222] Figure 5 The generally possible properties describing the possible states of implants and hard tissues are presented;

[0223] Figure 6 The generally possible properties describing the possible morphologies of both implants and hard tissues are presented;

[0224] Figure 7 presents general possible characteristics describing the quality of a potential connection interface that can be derived from state and morphological information related to a specific implant and hard tissue;

[0225] Figure 8 The effects of implant insertion on specific hard tissues and any fixatives present are generally demonstrated;

[0226] Figure 9 Generally showing a calculated internal virtual image of a perfectly connected joint and properties used to derive relevant quality indicators based on existing implant and hard tissue pairs;

[0227] Figure 10 In general, proposed changes to existing physical connection joints are presented that can be derived from a comparison between the joint itself and a virtual version of equal or greater quality;

[0228] Figure 11 is a detailed schematic flow chart depicting the preprocessing and operations required to transform the data into a more evaluable form for further use in predictive algorithms and methods;

[0229] Figure 12 is a detailed schematic flow chart depicting the types of predictive algorithms and methods that can generate information and characteristics related to the life and performance of a particular connection joint based on existing processed data;

[0230] Figure 13 is a detailed schematic flow chart depicting a process by which a set of corrective actions for modifying tissue morphology is determined; and

[0231] Figure 14 A computing device is shown upon which various embodiments described herein may be implemented, in accordance with an embodiment of the invention.

[0232] definition

[0233] The following definitions are provided as general definitions and in no way should limit the scope of the present invention to these terms alone, but are set forth for a better understanding of the following description.

[0234] Unless otherwise defined, all technical terms and scientific terms used herein have the same meaning as those of ordinary skill in the art to which the present invention pertains. It should be further understood that, unless explicitly defined herein, terms used herein should be interpreted as having the same meaning as the background of this specification and the meaning in the relevant field, and will not be interpreted with an idealized or overly formal meaning. For purposes of the present invention, additional terms are defined below. In addition, it should be understood that all definitions as defined and used herein cover dictionary definitions, the definition in the files incorporated by reference, and / or the ordinary meaning of the defined terms, unless in doubt about the meaning of a particular term, in which case the common dictionary definition and / or common usage of the term will prevail.

[0235] For the purposes of the present invention, the following terms are defined below.

[0236] The articles "a" and "an" are used herein to refer to one or to more than one (ie, to at least one) of the grammatical object of the article. For example, "an element" means one element or more than one element.

[0237] Unless otherwise stated or indicated, the term "about" or "approximately" is used herein to refer to a quantity that varies by up to 30%, preferably by up to 20%, and more preferably by up to 10% in the positive and negative directions relative to a reference quantity. The use of the term "about" or "approximately" to qualify a number is merely to clearly indicate that the numerical value should not be interpreted as an exact value.

[0238] Throughout the specification, unless the context requires otherwise, the words “comprise”, “comprises”, “comprising”, will be understood to imply the inclusion of stated steps or elements or groups of steps or elements but not the exclusion of any other steps or elements or groups of steps or elements.

[0239] As used herein, any of the terms "comprising," "which comprises," or "it includes" is also an open term, which also means including at least the elements / features following the term, but does not exclude other elements / features. Therefore, "comprising" means "including" and is synonymous with "including."

[0240] In the claims, as well as in the Summary of the Invention above and the Detailed Description of the Invention below, all transitional phrases such as "including," "comprising," "carrying," "having," "containing," "involving," "having," "consisting of," etc., shall be understood as open-ended, i.e., meaning "including but not limited to." Only the transitional phrases "consisting of" and "consisting essentially of" shall be closed or semi-closed transitional phrases, respectively.

[0241] The term "real time," as in "displaying real-time data," means displaying data without intentional delay given the processing constraints of the system and the time required to accurately measure the data.

[0242] The term "near real-time," such as "acquiring real-time or near real-time data," means acquiring data without intentional delay ("real-time") or as close to real-time as possible (i.e., with a small but minimal delay, whether intentional or not, within the constraints and processing limitations of the systems used to acquire and record or transmit the data).

[0243] Although any methods and materials similar or equivalent to the methods and materials described herein can be used in the practice or testing of the present invention, preferred methods and materials are described. It should be understood that the methods, devices, and systems described herein can be implemented in various ways and for various purposes. The description here is by way of example only.

[0244] As used herein, the term "exemplary" is used to provide an example rather than to indicate a quality. That is, an "exemplary embodiment" is an embodiment provided as an example, not necessarily an embodiment of exemplary quality such as to serve as a desired model or represent the best in class.

[0245] The various methods or processes outlined herein may be encoded as software that can be executed on one or more processors using any of a variety of operating systems or platforms. In addition, such software may be written using any of a variety of suitable programming languages ​​and / or programming or scripting tools and may also be compiled into executable machine language code or intermediate code that is executed on a framework or virtual machine.

[0246] In this regard, the various inventive concepts may be embodied as a computer-readable storage medium (or multiple computer-readable storage media) (e.g., computer memory, one or more floppy disks, compact disks, optical disks, magnetic tapes, flash memory, a circuit configuration in a field programmable gate array or other semiconductor device, or other non-transitory medium or tangible computer storage medium) encoded with one or more programs that, when executed on one or more computers or other processors, will perform methods for implementing the various embodiments of the present invention discussed above. The one or more computer-readable media may be transportable so that the one or more programs stored thereon can be loaded onto one or more different computers or other processors to implement various aspects of the present invention as discussed above.

[0247] The terms "program" or "software" are used herein in a general sense to refer to any type of computer code or set of computer-executable instructions that can be used to program a computer or other processor to implement various aspects of the embodiments as discussed above. Additionally, it should be understood that, according to one aspect, one or more computer programs that, when executed, perform the methods of the present invention need not reside on a single computer or processor, but may be distributed in a modular manner among multiple different computers or processors to implement various aspects of the present invention.

[0248] Computer-executable instructions can take many forms, such as program modules, that are executed by one or more computers or other devices. Generally speaking, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Typically, in various embodiments, the functionality of the program modules can be combined or distributed as needed.

[0249] Furthermore, the data structure can be stored in a computer-readable medium in any suitable form. For simplicity of illustration, the data structure can be shown as having fields that are related by their position in the data structure. Such relationships can also be achieved by allocating certain locations in the computer-readable medium for storage of the fields, which convey the relationship between the fields. However, any suitable mechanism can be used to establish the relationship between the information in the fields of the data structure, including by using pointers, tags, or other mechanisms that establish relationships between data elements.

[0250] Furthermore, various inventive concepts may be embodied as one or more methods, an example of which has been provided. The actions performed as part of a method may be ordered in any suitable manner. Thus, embodiments may be constructed in which the actions are performed in an order different from that shown, which may include performing some actions simultaneously, even though shown as sequential actions in the illustrated embodiment.

[0251] As used herein in the specification and claims, the phrase "and / or" should be understood to mean "either one or both" of the elements so united, i.e., the elements are present together in some cases and separately in other cases. Multiple elements listed with "and / or" should be interpreted in the same manner, i.e., "one or more" of the elements so united. In addition to the elements specifically identified with the "and / or" phrase, other elements may optionally be present, whether related or unrelated to those specifically identified. Thus, as a non-limiting example, when used in conjunction with open language such as "comprising", "A and / or B" may refer to only A (optionally including elements other than B) in one embodiment; to only B (optionally including elements other than A) in another embodiment; to both A and B (optionally including other elements) in yet another embodiment; etc.

[0252] As used herein in this specification and claims, "or" should be understood to have the same meaning as "and / or" as defined above. For example, when separating the items in a list, "or" or "and / or" should be interpreted as inclusive, i.e., including at least one element in a plurality of elements or a list of elements, but also including more than one element and optional other unlisted items. Only terms that clearly indicate the opposite (such as "only one of" or "exactly one of") or when used in a claim, "consisting of will refer to including exactly one element in a plurality of elements or a list of elements. In general, when preceded by an exclusive term, such as "any one," "one of," "only one of," or "exactly one of," the term "or" used herein should only be interpreted as indicating the exclusion of another alternative (i.e., "one or the other of them, but not both"). When used in a claim, "consisting essentially of should have its ordinary meaning used in the field of patent law.

[0253] As used in this specification and claims, when referring to a list of one or more elements, the phrase "at least one" should be understood to mean at least one element selected from any one or more elements in the list of elements, but does not necessarily include at least one of each element specifically listed in the list of elements, and does not exclude any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than the elements specifically identified in the list of elements to which the phrase "at least one" refers, whether related or unrelated to those specifically identified elements. Thus, as a non-limiting example, "at least one of A and B" (or equivalently, "at least one of A or B," or equivalently, "at least one of A and / or B") can, in one embodiment, mean at least one of A and B, optionally including more than one, such as A but no B (and optionally including elements other than B); and in another embodiment, can mean at least one of A and B, optionally including more than one. For example, there is B but no A (and optionally includes elements other than A); in yet another embodiment, it may refer to at least one of A and B, optionally including more than one, such as A, and at least one of A and B, optionally more than one, such as B (and optionally including other elements); etc.

[0254] For the purposes of this specification, where method steps are described in a sequence, that order does not necessarily imply that the steps are performed in that order in time, unless there is no other logical way to explain the sequence.

[0255] In addition, where features or aspects of the invention are described in terms of Markush groups, those skilled in the art will recognize that the invention is also thereby described in terms of any individual member or subgroup of members of the Markush group. DETAILED DESCRIPTION

[0256] In the following description, it should be noted that similar or identical reference numerals in different embodiments denote the same or similar features.

[0257] The following detailed description is an example of the present invention and should not be limited to a certain scope by the embodiments described, nor should it be understood in any way as a limitation to the broad description of the present invention set out above. These embodiments are described in sufficient detail to allow those skilled in the art to practice or implement the present invention. Unless otherwise stated, the precise shape, size and appearance of the parts described or shown are not what the present invention desires or requires. It should be understood that any embodiment in the embodiments mentioned or otherwise related may be subjected to any utilization, combination, or structural, logical, electrical and mechanical changes, variations, additions or modifications without departing from the scope of the present invention. Similarly, any functionally equivalent products, compositions and methods and all single, combined and sequential steps, features, structures, sequences, processes, compositions and compounds mentioned or indicated individually or together in this specification will also fall within the scope.

[0258] Unless otherwise indicated, the entire disclosure of all documents (including patents, patent applications, journal articles, laboratory manuals, books, diagrams, knowledge bases, and any other form of documents or other referenced resources) cited herein does not constitute an admission as prior art, prior knowledge or common knowledge required by those skilled in the art, or any other connection or assumption to the present invention.

[0259] Features presented through the drawings are represented using a numerical ordering of the stages of the invention to which they belong along with a logical ordering within the drawings themselves, with the exception of the first drawing which serves as an initial overview.

[0260] The present invention will be described with respect to embodiments related to analyzing a specific portion of orthopedic hard tissue and a corresponding prosthetic implant to determine the potential quality of their resulting joint based on prior procedures, the effects of the connection procedure, any changes that may be required after connection, and the performance and longevity of the connection. However, the present invention is more generally applicable to the field of analyzing a specific portion of tissue for an entity designed to fit or be positioned relative to that portion of tissue.

[0261] With advances in sensor technology and modern processing techniques, large amounts of data have become readily available and can be processed in a way that allows for the extraction of meaningful information. Sensors including optical, acoustic, three-dimensional, two-dimensional, environmental, and contextual sensors can be combined and configured to provide data about their corresponding objects.

[0262] This data can then be processed to derive insights and conclusions that were not otherwise known. There are many machine learning, data science, and mathematical algorithms and techniques for achieving this processing, all of which depend on the properties of the data, including its volume, dimensionality, precision, and redundancy.

[0263] Statistical analysis is a category of these data processing techniques that typically aims to generate summaries and measurements based on a dataset or the entire pool of data as a whole. These measurements typically provide insights into different characteristics of the data, such as the mean, standard deviation, variance, median, and range.

[0264] Supervised machine learning is another category of data processing techniques that typically aims to find patterns or trends within a specific dataset that can be used as indicators to map data to associated values. This means that the algorithm can search new data as it is presented, looking for the same or similar indicators to predict the associated value. This allows the algorithm to extract meaning from data, including optical and acoustic signals, where statistical measures such as mean or standard deviation are rarely meaningful. Generally speaking, it works like this: a machine learning algorithm or technique is first trained and then executed on new data.

[0265] Training involves processing a dataset and then using it and its associated ground truth to build an internalized model. The training process is generally divided into two distinct phases: a preprocessing phase and an operational phase. Preprocessing involves cleaning, rearranging, formatting, and deconvolving the data into a more useful form. Operations involve scaling or aligning the preprocessed data, breaking it down into its constituent or representative elements, and then aggregating the results if necessary. The resulting data can then be used to generate a model by looking for any patterns or trends in the data and mapping it to its associated ground truth.

[0266] Execution involves providing the trained algorithm with new data whose associated values ​​are unknown. The algorithm then processes this data in a similar manner to the training phase, looking for any patterns or trends that are similar to those already seen. The algorithm then matches the new data with the associated values ​​based on these similar indicators.

[0267] Embodiments of the invention disclosed herein are intended to improve the systems and methods used by surgeons during orthopedic prosthetic implant therapy to maximize the integration and survivability of the prosthesis by providing an alternative therapy that significantly reduces reliance on inaccurate measurement equipment; provides support to relevant personnel during layout; and makes educated predictions regarding potential problems and the lifespan of the resulting connection joints.

[0268] This is achieved by leveraging a combination of various sensors (e.g., physiological and / or optical sensors) combined with data retrieved and stored during multiple surgical procedures. The different types of sensors generate data based on individual subjects or combinations of subjects, which can be processed and interpreted to extract information that cannot be obtained manually. This is supported by algorithms and methods trained from historically generated data and related information that can predict the final outcome of the subject in question when given the same inputs related to the subject in question.

[0269] It should be understood that the present invention is not limited to orthopedic surgery, nor is it limited to any particular form or type of tissue or implant. Rather, the systems and methods disclosed herein may also be used in therapies such as implantation of medical devices or internal fixation.

[0270] Reference Figure 1 , depicts a schematic flow chart depicting an implant fit analysis process 10, which is divided into the various steps that make up the process. The information flow between these steps and the various processes they may include are described in an overview format. Data collection 100 utilizes a series of different sensors, which may be arranged alternately, to generate different amounts and types of data 100a based on an object, which may be the tissue of a patient undergoing a certain therapy or an implant or prosthesis planned to be implanted in the patient's body. Data processing 200 pre-processes and manipulates the data 100a to generate processed data 201 with increased usability and evaluability. Data interpretation 300 analyzes the processed data 200a and extracts useful information and structure based on the tissue and implant. Compatibility information 400 summarizes the types of individual or combined conclusions that can be generated by these interpretations 300a. This is supplemented by passing the generated compatibility information through various models and algorithms suitable for predicting the lifespan and performance of prosthetic implants 500. The model and algorithm used in the prediction step 500 is initially generated through a machine learning or training process based on the mapping relationship between historical compatibility information and the postoperative status of its patients. Once populated, new compatibility information 300a can be passed through, where the indicators identified therein will be mapped to corresponding values ​​related to implant durability, thereby predicting the potential state of the connection joint 561. The resulting prediction results 500a of implant performance and durability are used to inform the real-time calculation of possible corrective actions 600, which the surgeon can adopt while performing the treatment to improve the performance and durability prediction 500.

[0271] Figure 2 A detailed schematic diagram is depicted, which depicts the Figure 1Described implant cooperates the exemplary embodiment of the data collection step 100 of analytical process 10.Data are collected by a series of sensors, and the type, quantity and arrangement of these sensors can be different between many possible embodiments.Sensor in these embodiments can work independently, or works as the part of sensor system or sensor set, and each sensor cooperates in some way to improve the quality or quantity of sensed data in this case.Each sensor may be completely self-sufficient, or may need additional device or system to cope with all or part of required processing.

[0272] The physical arrangement of the sensors is advantageously placed around the object in every way possible to maximize sensing potential while minimizing interference with the surrounding surgical environment. If the sensors are present as part of a system in a collaborative setting, the arrangement of the sensors should reflect this, such as sensing the object from different angles and then combining the different views.

[0273] Depending on the specific system embodiment, the sensor can be automated, manually triggered, or controlled by a combination of automation and manual triggering. In the case where an appropriate sensing environment must be formed, when such an environment exists, manually controlling the sensor will be more appropriate. Manual control can be achieved by means of physical actuation that may include voice control, gesture control, and different forms. Due to the precise control provided to the surgeon or surgical assistant, manual control appears in the specific embodiments described herein. Of course, in alternative embodiments, it will be more advantageous to make the sensor work autonomously in conjunction with the computing program to provide information without the need for the physical intervention of the surgeon or his assistant. Variations of these modes may also exist, for example, once the sensor has sensed the required conditions, the sensor is automatically triggered, for example, the sensor can advantageously operate continuously in real time, and when sensing or observing a specific state, the sensor triggers further operations within the system, for example, generating an alarm to inform the surgeon that a certain condition has been obtained, or alternatively, identifying undesirable parameters and triggering the calculation of corrective actions to overcome or correct the undesirable state.

[0274] In further embodiments, the sensor may be configured to sense in a periodic manner, as the changes being sensed are unlikely to occur continuously and the sensor's sensing rate may be limited. In some embodiments, sensing may only need to occur once or may be continuous, providing a feed of information as close to real-time as possible. Where a snapshot or specific state is sensed, the provision of sensed data may be performed with a delayed time, as multiple states may be required to generate useful data.

[0275] The choice of sensors and their configuration will depend on the object being sensed. Typically, sensing of the implant and tissue will include at least one two-dimensional scanner (e.g., a 2D optical sensor array), a three-dimensional scanner (e.g., OCT, structured light sensors, or laser line sensors), and a hyperspectral or spectral sensor. These sensors should be positioned around the implant or the tissue at or near the implant site, with particular attention paid to areas where osteotomy is planned or has already occurred, as these are key areas of implant involvement. Some of these sensors can operate in real time and, if they have a clear line of sight, can be used for periodic sensing. Other sensors may be excluded from direct operation until staff have prepared the theater environment for ideal sensing conditions, and then restored after sensing occurs, for example, by removing the UV light source from the environment to avoid interference with an automated fluorescence measurement sensor. In both cases, the ability to automatically trigger the sensor in addition to its autonomous operation can be provided to a trusted person. Manual triggers will typically include physical buttons or touchscreen control interfaces for effective interaction.

[0276] Reference Figure 2 , the surrounding environment and the personnel involved should be prepared 101 for any sensing procedures that may occur based on the sensors being used. In certain embodiments, this may involve implicit preparation of the environment to ensure or increase the likelihood of optimal conditions occurring, as well as temporary explicit modifications of the environment if the sensors involved are unable to sense effectively under typical conditions. Such modifications may include having the staff move any obstructing equipment and adjust any environmental conditions, such as lighting. Certain embodiments will typically require some elements of implicit preparation and explicit preparation, as will be understood by those skilled in the art. Since orthopedic surgery is generally time-constrained from both a monetary and medical perspective, reliance on periodic sensors that operate around the typical operating environment of the surgical procedure may be more advantageous than sensors that require constant changes in setup and interruption of normal surgical procedure, although a small number of such occurrences during the procedure may be advantageous in significantly improving the surgical outcome at minimal cost to the surgical procedure itself.

[0277] The configuration of the sensors is prepared 102, taking into account any sensing procedures that may occur during the surgical procedure, assuming that the environment allows the surgical procedure to be possible or at least effective. This may involve changing the position, alignment, and orientation of the sensors both independently and in relation to each other. Additional equipment, such as a stand or platform, may be required for these changes. In certain embodiments, the sensors will already be in an optimized configuration as part of a pre-built system or platform. When the opportunity arises, the entire system can be moved into place in a relatively small time frame, thereby reducing environmental impact and interference with the surgical procedure. After the preparations 101, 102 have occurred, the sensing procedure can begin 103.

[0278] Sensing 103 is performed based on a set duration that determines the number of possible repetitions based on the specific sensor(s) used in the specific embodiment. In embodiments where the environment and sensor configuration need to be adjusted for optimal sensing conditions, these parameters may be constrained by the settings of the sensing conditions. During orthopedic surgery, this duration may be only a few minutes, as time is critical to its success, meaning that only a few hundred sensing repetitions may be possible. In embodiments that allow passive sensors, this duration may depend on the total lifespan of the object being sensed or the actions performed relative to the object, with the number of repetitions determined in a similar manner. After sensing is completed, previously performed preparatory measures 101, 102 can be resumed if necessary.

[0279] Data may also be collected directly through provisions from a verified person or system 104, which may include files, records, and databases that may be derived from the surgical procedure or sourced from external repositories, such as current or historical patient records. In certain embodiments, such external sources may include any resource that can provide additional information about the patient or their ongoing procedure, such as patient records, medical records, and historical surgical or surgical data.

[0280] All sensed and provided data will be collected and presented in an easily accessible format, as required for the necessary processing in step 200 105 . Data collection preferably involves extracting data in a format deemed most useful, which is generally determined by the sensor from which the data originated. The sensory data obtained from multiple sensors may initially appear in a raw format and must be converted into a form easily accessible to the data processing step 200 , so that meaningful calculations can be performed on the collected data and meaningful analytical and predictive results can be derived therefrom. This formatting of the raw sensor data can advantageously be performed by an external control unit. Similarly, the provided data may appear in an inaccessible form, such as paper, requiring manual entry into a digital system to make it accessible to the data processing system. In certain embodiments, all data will advantageously be stored in the same manner so that it can be accessed in the same way. This storage method is ideally the random access memory (RAM) of a central system, although solid-state drives or hard disks may be used instead, depending on the raw volume of data and the processing speed required for data processing. In alternative embodiments, a database may be used to store and access this data. Such databases can use the strict storage and access guidelines imposed by SQL, or be made more flexible and scalable by using technologies such as NoSQL.

[0281] Figure 3 A detailed schematic diagram is shown, which depicts the Figure 1 Depicted are exemplary data processing steps 200 of the implant fit analysis process 10. Data processing involves the preparation and manipulation of data to transform the data into a form that is generally more useful in terms of both its usability and evaluability.

[0282] The collected data 201 will typically be in some raw format that may contain noise, errors, or redundancy. If data containing such defects is used unprocessed during normal processing, it may lead to unnecessary calculations, inconsistent, or erroneous results. Therefore, depending on the type and severity of the defects, they must be repaired or removed 202.

[0283] Noisy data can be defined as data that is partially correct but contains other degraded or erroneous data. The ratio of correct to erroneous data provides an indication of the type of action that can be taken in response. If there are only a few errors, this small amount of erroneous data can be repaired based on the correct data, or it can be removed, assuming the remaining data provides sufficient benefit in its reduced form. However, if the amount of incorrect data is large, removing the data entirely may be the only option.

[0284] Error data may be defined as data that is erroneous and contains values ​​that could not possibly exist through the medium in which the error data was created or in relation to the surrounding data. In most scenarios, error data cannot be repaired because it is generally unrelated to the expected value and is therefore typically removed.

[0285] Redundant data can be defined as data that, while not erroneous, does not add any additional value or benefit to the dataset as a whole, but only increases its volume and introduces inconsistencies. Redundant data cannot be repaired because it is technically correct, and is therefore typically removed or ignored.

[0286] Whether to remove or repair data depends largely on the source and format of the data, as well as the severity of the error in question. Removal is relatively simple, depending on the format, but the remaining data is left in a streamlined state. In some cases, the data will remain valid, but in other cases additional modifications may be required to achieve this. This may require combining the remaining data with other streamlined data sets to create a complete set, or replacing the data with dummy data that will not affect the final result. In contrast, repairing data is more difficult and requires knowledge of the expected structure to determine what is missing or erroneous so that it can be corrected. The techniques for achieving this are highly dependent on the data itself and may not even be feasible. In certain embodiments, all redundancies and errors are directly removed, while any noise is repaired if additional benefit can be discerned.

[0287] Often, the collected data 201 will need to be rearranged and formatted to make it more accessible and store it more logically for processing 203. This is because its original form will likely be based on the order and format of its source (such as a specific sensor, system, or group of people), which may not be optimal for operation.

[0288] In certain embodiments, rearrangement involves collecting data from multiple sources and categorizing it so that data that is similar or can be used in similar ways, despite originating from different sources, is grouped together. This allows for searching data based on its attributes and for finding related data within the same vicinity. Formatting includes various structures that increase accessibility to different groupings of data types that can be manipulated simultaneously and subsequently. Other embodiments may have different formatting and arrangement methods depending on their application.

[0289] The collected data 201 can be sampled 204 to create different segments that provide additional utility compared to operating on the data as a whole. Sampling 204 can include streamlining the data pool into a more representative pool of data, whereby, while the data pool may contain a smaller amount of data, the value or benefit generated by the data as a whole is the same or advantageously commensurate with the full data set. Sampling can also include splitting or dividing the data pool into separate segments, each of which has a different purpose, typically defined by how it is used. This can include different segments for averaging, testing, training, and / or validation, as required.

[0290] In certain embodiments, the entire data pool may first be reduced to a more representative sample so that the computational load can be reduced and the remaining data can be more easily interpreted. The reduced sample is then divided into a plurality of different segments.

[0291] In a particular embodiment, the reduced sample may be divided into four different segments, wherein the division of the data pool yields the best final result over any other division.

[0292] The first two larger segments will serve as the primary data source, with all relevant processing performed within them aimed at extracting the available information. The results for each individual segment can then be compared or averaged to ensure that the results seen from processing one of these segments are a result of the processing, and not inherent characteristics within the data itself or due to any other inconsistencies. Comparisons can be performed similarly between individual segments and certain combinations of results from these segments to monitor the impact of additional or different data on accuracy or derivable information.

[0293] The remaining smaller segments can be used to test the performance and effectiveness of the larger segments. This will primarily be combined with machine learning data processing techniques, data science, and mathematical algorithms or methods as understood by those skilled in the art to determine how accurate the calculations are actually performed and whether they can be performed on data that has not yet been seen.

[0294] Other embodiments can be implemented that determine the splitting of the collected data based on the intended application and the processing to be performed on the data. It may be advantageous to use the data as a whole or to use multiple sets of data and average them to arrive at a solution. Similar combinations or approaches can also exist for data segments that are not directly involved in data generation (e.g., test segments and validation segments), although these data segments may not necessarily exist.

[0295] The collected data 201 may need to be scaled or aligned to make it easily comparable 205. This is because values ​​provided from different sources, or even the same source, may differ drastically in scope, even though they may represent or describe the same instance. By shifting the scope to the same point, comparisons can be made easier, and processing algorithms or methods with this requirement become feasible.

[0296] In certain embodiments, this will be performed for all values ​​originating from the same source during a single sensing action, and may also be performed for all sensing actions, depending on how different their respective contexts and environments are. Data from different sources may not be scaled together because their representations may be too different, and the processing required to produce comparable representations may reduce their overall usefulness. Other embodiments may scale depending on the sensors used, the intended application of the sensed data, and the processing of that data.

[0297] The collected data 201 may be streamlined, split, or decomposed 206 into their constituent elements, or individual elements including data for identifying and using only the primary beneficial elements rather than all elements.

[0298] This decomposition will reduce the amount of redundancy that exists and subsequently reduce the computational load since the remaining elements will no longer be processed. However, this is based on the assumption that the constituent elements possess the vast majority of utility, or at least enough to make any small amount of utility that the remaining data possesses insignificant or provide less benefit than the reduced computation.

[0299] Selected components may remain relevant to a specific application or form of processing, while the remaining data is either unusable or does not produce meaningful information in this context. This is particularly evident in machine learning, data science, and mathematical algorithms or methods, as component elements are often good indicators when used in various complex mapping processes.

[0300] In certain embodiments, if a particular element or series of elements better represents the data than the entire data set as a whole, the data will be decomposed into its component elements. The component elements will also be used in conjunction with machine learning, data science, and machine learning algorithms or methods to improve their predictive accuracy, especially in scenarios where the component elements are relatively more accurate. Other embodiments will likely decompose the data into its component elements to some extent, typically for the same reasons as the previously discussed embodiments, but may differ in number and scenario.

[0301] The collected data 201 and possible constituent elements can be aggregated together 207 to create a single entity that has more utility than the individual data or elements that make it up. This also reduces the amount of redundant calculations involved by streamlining the data available for a single expression.

[0302] The aggregation method 207 depends largely on the application, type, and presentation of the data, as well as the form of processing to be used for its results. Simple methods may involve, for example, averaging the data involved, while more complex methods may involve, for example, providing weights for each individual element and executing procedures to process and combine the individual elements based on these weights. As the amount of information related to the data and the context of the application increases, the complexity and utility provided by these aggregation methods may also increase.

[0303] In certain embodiments, data or constituent elements may be aggregated 207 together when the aggregation provides greater benefit than would otherwise be achieved individually. Aggregation can be performed on all data sources, but may be limited to data from similar sources, as different aggregation algorithms may require a certain level of similarity to be effective. Other embodiments may aggregate data in similar ways, with their dependencies determining how and to what extent aggregation occurs.

[0304] In addition to those mentioned above as required, other processing methods 208 may optionally be utilized 208 as will be appreciated by those skilled in the art. The order and presence of data processing steps employed in a particular embodiment may not necessarily reflect the order and presence of the manner 209 described herein. For example, depending on the requirements of the form of the collected data, the specific data processing steps used for a particular application may include any useful selection of available data processing steps 209, and such selected steps may be applied in any suitable order.

[0305] Now go to Figure 4 , shows a detailed schematic diagram, which depicts the Figure 1 Depicted is an exemplary data interpretation step 300 of the implant fit analysis process 10. Data interpretation involves analyzing 301 the processed data in an evaluable form to generate information and statistics that can describe various characteristics based on the data.

[0306] Measurements defined by mathematical or statistical equations, theories, or concepts can be calculated 302 to generate summary information based on the evaluable processed data 301 obtained from the data processing process 200. These calculations will typically produce a single value that can describe a specific characteristic or series of characteristics related to the data being used. This may include measurements such as the mean, standard deviation, and variance of the data. These calculations should be performed on processed data sets or samples that contain a certain degree of similarity, because if the data are completely independent, the results will reflect this independence, which may have little practical application.

[0307] While the measurements themselves may not allow conclusions to be drawn based solely on them, they have alternative utility in providing reinforcement for conclusions reached through other means of interpreting the data. This may be their primary purpose, especially when the desired conclusions are quite complex.

[0308] In certain embodiments, these calculations are performed on all data samples that are similar enough to produce a useful result, where the similarity can be based on the source of the data sample, its processing method, or its object. Other embodiments will likely perform these calculations similarly, although the data sets they use as input may vary depending on their application.

[0309] Custom, specialized, or standardized metrics can be calculated 303 to generate information based on the evaluable processed data 301. These calculations are typically based on the data itself and its representation, which in turn is closely related to the origin of the data or, more specifically, the specific sensor that generated the data (assuming the data was indeed generated by a sensor). This means that these calculations are largely application dependent and may not be included in all embodiments, although if an embodiment does have the conditions and capabilities required to utilize them, it is likely to do so. Such calculations can include calculations based on image colorization, acoustic signal wavelength, or position readings.

[0310] A customized or proprietary calculation is one that applies only to a specific situation and may have been created or modified specifically for that purpose. In contrast, a standardized measure is one that is created and maintained by a standards organization and has the same meaning and equations regardless of its object or the data it is supplied with.

[0311] In certain embodiments, customized measures and standardized measures are each used in situations where they can benefit. The customized measures will primarily consist of measures directly related to a medical procedure or surgical procedure, such as determining the mechanical axis of a particular knee joint. The standardized measures will primarily be derived from the International Organization for Standardization (ISO) and may include measures based on geometric measures, structural measures, and morphological measures. This will allow properties including surface flatness and roughness to be calculated in a comparable manner. Other embodiments may utilize surface flatness and roughness, as long as they exist in situations where this is permitted.

[0312] Machine learning, data science, and execution of mathematical algorithms or methods 304 may be used to generate predictions based on the evaluable processed data 301. These predictions will typically detail certain attributes of the data that cannot be definitively discerned with varying degrees of accuracy.

[0313] Predictive algorithms and methods come in many different forms, separated by their usage requirements. The amount and quality of the data provided to them determines their level of accuracy, and therefore their usability. Ideally, each set of provided data should be reasonably independent and large enough to allow the predictive algorithm or method to understand why the data is in that dataset and any edge cases that may exist.

[0314] The data passed to these predictive algorithms or methods typically cannot be used in their raw state, but must be processed in a specific way based on the predictive analysis. This can involve converting the data into a more accessible form, which is increasingly simpler and easier to use, often consisting of specific components, before converting it back into a more evaluable form.

[0315] In certain embodiments, supervised algorithms or methods will be the primary form of predictive analytics. These supervised algorithms or methods work by mapping input data to a value or set of values ​​using metrics determined based on previous historical data. This process involves two main steps: training and execution.

[0316] Training involves providing an algorithm or method with a large amount of data and the corresponding value or set of values ​​for each algorithm or method. The algorithm or method then examines the data and the corresponding values ​​to identify which indicators in the data result in which values. Based on this mapping, a computational structure is created that receives the data as input and returns the corresponding values ​​as output based on the indicators contained in the data.

[0317] Execution includes passing new data to this structure / model, which will extract relevant indicators from the new data and then return a corresponding value or set of values, which may, for example, include a calculated value representing a numerical prediction of the implant performance and life prediction of the orthopedic implant.

[0318] Evaluation of the evaluable processed data 301 can be performed manually by certified personnel or through prior documentation 305. In certain embodiments, this evaluation involves a surgeon or other medical practitioner reviewing the data as it is generated and providing conclusions and insights based on their experience, which can be used to train computational models used to analyze the data. Similar conclusions can also be provided preoperatively based on medical records, which can inform the various processes and approaches described herein.

[0319] The data analysis may be performed to varying degrees by the sensor itself or by an attached control unit 306. This may be very data dependent, such that the analysis provided may be based on properties or characteristics for which the particular sensor is specifically designed.

[0320] The results of this internal analysis can be beneficial independently or can be used as additional data that can be included as evaluable processed data 301 to assist and be processed by subsequent interpretation methods. In certain embodiments, both approaches can be used, as it will be assumed that the internal sensor processing can generate useful information independently and as part of a larger data pool.

[0321] In addition to those interpretations mentioned above, there may be other interpretations 307. The order and existence of these interpretations may not necessarily reflect the order and existence of the interpretations 308 described herein.

[0322] Figure 5 An exemplary implant and tissue interface is shown, wherein the respective states of the implant and tissue are summarized as follows Figure 1 A portion of a description of an exemplary compatibility information generation step 400 of the implant fit analysis process 10 is depicted. State refers to the condition of an implant 401 or tissue 402 at a specific given moment, which is typically determined intraoperatively. State can be interpreted as a set of properties that can be used to describe a specific part or region thereof.

[0323] Implant Status 404 includes a series of descriptors that provide information about the physical implant's construction and integrity. Composition 405 describes the type of material that the implant can be made of. Certain materials may degrade faster, be more susceptible to damage, or cause a reaction when used against certain types of tissue. Deterioration 406 can describe the current state of the implant and the rate at which the implant naturally degrades when inserted. If the implant has begun to degrade or the rate of degradation is accelerated, leaving it inserted may result in reduced lifespan and performance for the patient. Density 407 can describe the compactness of the particles present within the implant and will provide an indication of the implant's hardness and how well it can respond to external trauma. Particle Dissolution 408 is the rate at which material particles can be expelled from the implant and how this rate changes over time. These particles are generally seen as foreign matter in the patient's body and may cause an internal reaction that can damage the connecting joint between the implant and the tissue.

[0324] Tissue state 410 includes a series of descriptors that provide information about the health of the patient's tissue at the implant site. Composition 411 describes the types of minerals that make up the tissue. Different minerals and their abundance can generally serve as reliable indicators of the health and age of a particular tissue, and these characteristics can change significantly when they vary. This is further reinforced by tissue density 412, which defines how tightly packed these minerals, or at least specific minerals, are relative to each other. Hydration 413 describes the amount of water present within the tissue, which can be helpful in measuring the impact of any previous osteotomy and determining the timing of implant insertion. Necrosis 414 is the death of tissue cells, which can be caused by the osteotomy method or internal problems within the body. Coloration 415 is the specific color exhibited by the tissue, with any changes often indiscernible without advanced visual sensors. Reflectance 416 measures how much and what color the tissue can actively reflect. Thermal consistency 417 measures the temperature of the tissue and how that temperature is distributed across the tissue. Measuring thermal consistency is often a good way to monitor how the tissue is affected during osteotomies and other procedures.

[0325] These status descriptors will be based on Figure 4The interpreter 308 described in detail in the present invention is generated, and can include any patient-specific condition or structure or be affected by it.Depend on available data source and the description type that may be useful to specific application, may not generate all descriptors.As a part of specific embodiment, the implant state descriptor 404 and tissue state descriptor 410 explored herein are state descriptors that can be used to determine the compatibility between implant and tissue, yet as those skilled in the art will appreciate, can have other implant state descriptors 409 and other tissue state descriptors 418.

[0326] Figure 6 An exemplary implant and tissue interface is shown, wherein the respective morphologies of an implant prosthesis 401 and a patient tissue 402 are outlined as shown. Figure 1 A portion of a description of an exemplary compatibility information generation step 400 of the implant fit analysis process 10 is depicted. Morphology refers to the form, shape, or structure of an implant 401 and tissue 402, which is typically determined intraoperatively. Morphology can be interpreted as a set of properties that can be used to describe a specific part or region thereof.

[0327] The morphology 421 of implants and tissues includes a series of descriptors that provide information related to their morphology, shape, and structure. Generally speaking, shape 422 describes the geometric shape in terms of its contour and quality. This descriptor is a fundamental starting point for determining the morphological compatibility between an implant and tissue, as it will define whether the implant and tissue can actually fit together. If the shape of either would cause interference when connected, insertion may not be possible. In certain embodiments, the distance between the contours of the respective shapes of the implant and tissue should be as small as possible during insertion. Porosity 423 describes how many small physical pores a solid can contain and the size and distribution of these pores. Stiffness 424 describes the degree to which a particular entity is fixed in place, in terms of the degree to which it cannot move or bend into a different shape. Although not necessarily important when used with a single entity, stiffness can provide a measure of connection possibility and fault tolerance when used with two or more entities.

[0328] Flatness 425 describes the deviation between the height of the peaks present on a particular surface and their average height. If this deviation is relatively large, then it can be assumed that this surface has a low flatness, and if this deviation is relatively small then on the contrary. This definition usually depends on background and application, but if the surface has an uneven distribution but allows objects to be arranged flushly on the top, then this surface still can be considered to be flat. In a specific embodiment, flatness will be defined according to ISO standards. If this explanation peaks and valleys present in the surface do not exceed a predetermined limit, then this surface can be considered to be flat. This limit may be set to 0.3mm, which is the maximum gap required for reducing postoperative problems such as aseptic loosening. All surfaces of tissue 402 may need to be flat, so as to adapt to the surface of implant 401.

[0329] Parallelism 426 describes the deviation and distribution of peak heights between one surface and another surface. If their peak heights and distributions are similar, then it can be assumed that the two are parallel. This definition also typically depends on the context and application in which it is used. In a particular embodiment, parallelism will be defined according to ISO standards. This indicates that if the peaks and valleys of a surface (based on its current angle) do not exceed a predetermined limit, then the surface can be considered to be parallel to a specific reference plane or other surface. All corresponding surfaces between implant 401 and tissue 402 may need to be parallel to ensure maximum contact. This may mean that the predetermined limit should be minimum.

[0330] Roughness 427 describes the regular irregularities of peaks and valleys that affect the surface. These regular irregularities are often caused by specific machining processes or natural biological growth. In contrast, waviness 428 refers to abnormal irregularities and tends to be more widely spaced or composed of longer wavelengths. Waviness is generally considered a broader form of roughness. It is often caused by tool bending, vibration, or heat treatment. In certain embodiments, the roughness and waviness of the tissue can be advantageously controlled to match the roughness and waviness of the implant to promote osseointegration.

[0331] These morphological descriptors are usually based on Figure 4 Descriptors 421 are generated by the interpreter 308 described in detail in

[0066] and may include or be affected by any patient-specific condition or structure. Depending on available data sources and the type of description that may be useful to a particular application, all descriptors may not be generated. As a part for a particular embodiment, the descriptors 421 explored herein are descriptors that may be used to determine the compatibility between an implant and tissue, yet other implants and tissue morphology descriptors 429 may be present.

[0332] Figure 7 An exemplary implant and tissue connection joint is shown, wherein the associated compatibility information of the connection joint is summarized as follows Figure 1Depicted is a portion of a description of an exemplary compatibility information generation step 400 of the implant fit analysis process 10. The compatibility information 400 refers to characteristics, features, and attributes related to the quality of a connective joint 403 that exists between a particular implant 401 and tissue 402.

[0333] Tissue health 442 includes the tissue state 410 of the patient's tissue 402 and how both the implant therapy and the implant itself will affect that tissue state. This is divided into two different considerations. The first consideration involves whether the tissue can exist within the connecting joint 403. If the health of the tissue is severely deteriorated (which may be the case in some patients), replacement therapy may not be beneficial or recommended. This may also be the case if the tissue health does not allow it to properly assist the joint, for example, if its potential for osseointegration is relatively low and it may react negatively to various types of fixatives. The second consideration is how the tissue exists in connection with the implant, or more precisely, how suitable the material of the implant may be.

[0334] Implant material suitability 443 encompasses the condition 404 of the implant 401 and involves two main areas that are closely linked:

[0335] What the implant might affect, for example, if the implant is composed of a material known to be relatively brittle and therefore prone to dissolution of a large number of particles, an internal reaction could occur, potentially leading to damage to the joint. The same could occur if the material, through contact with tissue, triggers a natural reaction, such as an allergic reaction.

[0336] How the implant itself may be affected: For example, depending on the joint being replaced, regular stresses are expected based on the patient's movements. However, if this stress becomes too great or too frequent, trauma may occur. This can make the implant increasingly susceptible to further stresses and potentially cause or exacerbate problems with its connection joint. This information, combined with tissue health, will provide insight into how the tissue and implant will interact as part of the connection joint 403.

[0337] Involved implant insertion possibility and difficulty 444 is included in that after carrying out sufficient preparation, the form 421 of implant and tissue is compared to determine the possibility of connecting them.This generally relates to one of following two different scenarios.The first scenario is not yet carried out required osteotomy or it does not reach required depth, because tissue is too large, therefore can not insert.The second scenario is to have carried out required osteotomy and it exceeds required depth.This means that the distance between the profile of tissue and the profile of implant will be very large, therefore although inserting is relatively easy, the quality of resulting cooperation will be low.In a particular embodiment, can obtain the result that falls between these two scenarios, so that the distance between the profile of implant and the profile of tissue is minimum.

[0338] The degree of contact 445 during insertion details the quality of the fit or connection joint between the implant and the tissue. If the degree of contact is small, or if the contact is distributed in an uneven or irregular manner, the resulting connection joint can be considered poor. This is because the less contact there is throughout the fit, the greater the difficulty of successfully integrating the tissue into the implant. Instead, only several sections will be properly attached, which means that when the joint is under pressure, these sections will be disproportionately affected and wear out faster. When using a fixative in the connection joint, this effect is not as obvious, but it is still important because if not all areas of the implant are in contact with the fixative, the same problem will occur. In contrast, if there is a large degree of contact and the contact has a uniform distribution, the resulting connection joint can be considered as high quality. This is the desired result of the specific embodiment discussed above.

[0339] Implant thread filling and distribution details how well the surface of the tissue is molded to receive the degree 446 of the implant thread in a favorable manner. The implant thread is a specific coating on the entire implant surface that is intended to promote the osseointegration of the tissue. This will likely include: a certain proportion and distribution of peaks and valleys that match and insert respectively into the corresponding valleys and peaks of the implant thread. This can be based on the form of the thread itself, rather than any specific implant, because the thread pattern will likely be independent of the implant. In a particular embodiment, the surface of the tissue will advantageously match the thread of the implant, thereby enabling a higher level of osseointegration.

[0340] This compatibility information will be based on Figure 5 and Figure 6 The tissue and implant characteristics detailed in 404, 410, 421 and Figure 4Compatibility information 400 is generated using the interpreter 308 described in detail in

[0065] and may include or be affected by any patient-specific condition or physical structure. Depending on the available data sources and the types that may be useful for a particular application, it may not be possible to generate all the compatibility information. As part of a particular embodiment, the compatibility information 400 explored herein is the compatibility information that can be used to define the compatibility between the implant and the tissue, although other compatibility information 447 may exist.

[0341] Figure 8 An exemplary implant and tissue connection interface is shown, where the effects of the insertion process are outlined as follows Figure 1 A portion of a description of an exemplary compatibility information generation step 400 of the implant fit analysis process 10 is depicted.

[0342] Inserting the implant into the tissue during the operation is not an easy task. Usually, this requires a lot of physical strength from the surgeon or other participants. This is especially evident when tissue has undergone multiple osteotomies to ensure that its (at the connection joint 403) post-osteotomy form is as suitable as possible for the implant, thereby leaving only a slight gap for insertion. According to some documents, this will be interpreted as the maximum distance of each point of tissue 402 from implant 401 being 0.3mm.

[0343] Therefore, problems or damage may occur to the tissue 402 and the implant 401 (either to the tissue or to the implant) during the implant insertion process, although the implant is much less likely to be damaged. This typically requires damaging or destroying various post-osteotomy details along the surface of the tissue (e.g., at the connecting joint 403). For therapies based on osseointegration, this would include destroying the peaks and disrupting their distribution 461, thereby producing an imperfect joint surface, such as Figure 8 For a fixative based therapy this would involve regularly spreading the fixative so that some areas 462 may have more fixative than other areas.

[0344] While this may not adversely affect fixative-based therapies, for therapies that rely on osseointegration, the process substantially alters tissue morphology. Based on these alterations, it is possible that the new morphology may result in a lower-quality joint. This may create or increase the likelihood of certain postoperative problems.

[0345] The extent of peak disruption or fixative shift can be analyzed and predicted prior to insertion based on previously compiled compatibility information 400, such as Figure 7This evaluation can be used to inform the generation of other compatibility information and can prompt the regeneration or recalculation of compatibility information that may already exist. It is performed as many times as necessary, for example, to maximize implant performance and life prediction in step 500 of the implant fit analysis process 10. In certain embodiments, each time the compatibility information generated around the implant, tissue, or their resulting connection interface changes, this will be interpreted.

[0346] Figure 9 A partially simulated implant 401, tissue 402, and resulting joint 403 are shown to assess the ideal placement of the implant as a Figure 1 A portion of a description of an exemplary compatibility information generation step 400 of the implant fit analysis process 10 is depicted.

[0347] The layout can include many different measures and characteristics, which can include, for example, the degree of contact between the implant 401 and the tissue 402, the angle of the implant relative to the tissue, and the stress distribution on the implant.

[0348] A virtual image based on the morphology of the implant 472 and tissue 473 can be generated. An ideal layout 471 can then be derived from these individual virtual images, with the previously generated compatibility information 400 guiding this process. In certain embodiments, the generation of the compatibility information can involve determining the maximum amount of contact possible between the implant and the tissue, the most favorable angle for implant insertion, and the amount and possible distribution of any disruption and / or dispersion or displacement of any added fixative.

[0349] The results of physically inserting the implant into the tissue can be compared to the ideal layout to determine how closely they fit together and what may need to be changed to minimize this discrepancy. This may involve using various sensors or other measuring devices to generate information based on the physical fit. This device may be a general purpose device, a dedicated device, or a device such as a reference device. Figure 2 The data collection process 100 is detailed previously using the equipment structure and may need to be compared with the respective references Figure 3 and Figure 4 The processing and interpretation are similar to those detailed in processes 200 and / or 300. The information generated based on the physical fit and the simulated fit may require a certain degree of similarity in order to be compared.

[0350] Feedback based on the comparison can be quantitative or qualitative. Quantitative feedback can include instructions that provide information about how much adjustments should be made to the existing implant or tissue to achieve a more favorable comparison. Figure 10The types of indications that can be used are demonstrated, including movement of the implant or tissue in all spatial directions 491 , 492 , and 493 and rotation of the implant or tissue about all rotational axes 494 , 495 , and 496 .

[0351] Qualitative feedback can include suggestions or additional tips based on the insertion process. This can include analyzing the amount of force used and whether it should be increased or decreased, historical patterns or preferences for specific insertion issues, and whether the insertion angle is non-optimal.

[0352] If the insertion is deemed unfavorable beyond a certain limit, the insertion can be reverted. In this scenario, the simulated fit, physical fit, and some additional calculations, such as the surface damage or fixative displacement predictions discussed above, will need to be repeated.

[0353] Figure 11 is a detailed schematic diagram, which depicts the Figure 1 The data processing portion of the exemplary implant performance and life prediction step 500 of the implant fit analysis process 10 is depicted. The processes and steps involved are similar to those of FIG. Figure 3 The process and steps detailed in procedure 200 are very similar, except for the data source and the intention behind processing the data.

[0354] The data sources involved are the original compatibility information, medical records, and other patient data generated (e.g., from appropriate sensors during therapy) or acquired from external sources 501. This data should contain enough information to determine how compatible the implant is with its associated tissue, as well as details of the affected patient's health and lifestyle.

[0355] The intention behind processing data is to best prepare the data 501 for training and execution within predictive algorithms and methods. This can involve different types of preprocessing and manipulation to transform the data into a form that yields the greatest benefit for this purpose.

[0356] Pre-processing 502 data involves converting the data into a form with better usability in order to prepare for and generate maximum utility 508 from subsequent data operations. This data may initially be in an inappropriate form, most likely for describing a specific connection joint 403. Since this purpose is different from the expected predictive analysis, at least some portions of the data provided may be considered to be noisy, erroneous, or redundant and may be processed as discussed above. Because this may introduce inconsistencies in subsequent processing. In order to minimize the risk of this inconsistency affecting the results, all defective portions or other problems present in the data should be purified 503 by removal or by repair as discussed above, as long as the amount of benefit generated by the repaired portion outweighs the workload required to achieve the purified data. In a specific embodiment, defective data can be removed immediately unless there is a feasible path to repair them.

[0357] As part of the pre-processing step 502, the patient data 501 may need to be rearranged and formatted 504 to improve its efficiency and make its storage more logical for various predictive methods. The current form of the patient data may reflect its use in describing the joint 403 between the implant 401 and the associated tissue 402 and may be presented in a manner that increases its efficiency, which may not be optimal for predictive analysis.

[0358] In certain embodiments, and particularly for anticipated prediction methods, the rearrangement step 504 includes grouping data that may have established similarities or other relationships. This makes accessing or searching related data or data that clearly represents a particular aspect or series of aspects easier and more efficient. Formatting may include structuring these different groupings in a manner that allows for simultaneous and subsequent manipulation and analysis of the different data sets. This makes traversing from one data set to another related data set relatively simple and computationally inexpensive. Other embodiments may have different formatting and arrangement methods, depending on the type of manipulation intended for the data and the subsequent prediction method.

[0359] As part of the pre-processing step 502, the patient data 501 can be sampled 505 to create different parts that can provide additional utility compared to operating on the data as a whole. Sampling 505 includes reducing the data pool to a data pool that is more useful for a particular type of use, such as reducing the data as a whole to only parts that can be considered representative.

[0360] In certain embodiments, and particularly for a desired prediction method, the data 501 is first sampled 505 to create a single data pool that is more representative than the data as a whole. That is, the utility provided by this representative data pool should be equal to or better than the original utility. This representative pool is then divided into three distinct segments. The first, largest segment, referred to as the training set, is used to train the prediction algorithms and methods. The second, smaller segment, referred to as the test set, is used to test the trained prediction methods. The third segment, also smaller than the training set, referred to as the validation set, is used to verify that the trained prediction methods' results have achieved favorable accuracy relative to the test set.

[0361] Other embodiments will likely use similar sampling approaches consistent with the predicted approach, although additional customizations may be made according to their specifications.

[0362] Manipulating 508 the patient data 501 involves converting it into a form that is superior in evaluability to prepare for and maximize utility from subsequent predictive algorithms or methods 513. This data may initially be presented in a form where each value exists based on its original representation. Because each representation may differ in the data, achieving an appropriate level of comparability between different sets may be infeasible, or may be achieved to a suboptimal degree. By scaling or aligning these values ​​to the same point 509, comparability between different sets is increased.

[0363] In a preferred embodiment, and particularly for the intended prediction approach, all values ​​present in the data set that can be considered comparable and have a directly or similarly equivalent initial representation should be scaled 509. This is because certain types of predictive analysis generally work better when all data are within a known range. This also makes it easier to manipulate and differentiate the data, particularly when presenting the data (if such a need arises). Other embodiments will likely use similar scaling techniques, which will also be based on their intended prediction algorithm or method.

[0364] As needed, as part of data manipulation, patient data 501 can be streamlined, split, or decomposed 510 into its constituent elements. These resulting individual elements constitute the data and can be used to identify which existing features may be more beneficial or representative than others. This is very important for predictive analytics, as these types of features can generally provide good indicators, which can greatly improve its usefulness.

[0365] In certain embodiments, and particularly for contemplated prediction methods, data is decomposed 510 into constituent elements if these individual elements or other characteristics can be seen to contribute substantially in determining a comprehensive description of the data as a whole.

[0366] As part of the data manipulation, the provided data 501 and the constituent elements derived therefrom may be aggregated 511 together into a single entity. The aggregate entity should provide more utility than the individual elements or data used to create the aggregate entity, however this may not be the case if the decision is made from a storage or computational perspective.

[0367] The way in which aggregation is done typically depends on the type and representation of the data or constituent elements involved. Elements may need to share a certain degree of similarity or equivalence to be considered for aggregation.

[0368] In certain embodiments, and particularly for the intended prediction approach, if this will yield additional utility, then elements should be aggregated 511 together. This means that if the aggregated entity better indicates the characteristics of the data set than the individual elements, then the aggregate should be maintained.

[0369] After the provided data 501 has been pre-processed 502 and operated on 508 as needed, final processed data 514 is generated. Other pre-processing methods 506 and operation methods 512 may exist beyond those explicitly outlined herein and do not necessarily have to be performed 511 in the order presented, or at all. The determination and ordering of methods depends entirely on the available data and the intended application.

[0370] As those skilled in the art will appreciate, in addition to the above-mentioned methods, other pre-processing methods 506 and operating methods 512 may also be appropriately utilized. The order and existence of these pre-processing methods 507 and operating methods 513 may not necessarily reflect the following. Figure 11 The order and existence of the manner depicted.

[0371] Figure 12 A detailed schematic diagram is shown, which depicts the Figure 1 Depicted is the information prediction portion of an exemplary implant performance and life prediction step 500 of the implant fit analysis process 10. This involves using three different data sources in a range of different predictive approaches to generate information and values ​​that can provide insights into how long the implant will last and the causes of its degradation, if any.

[0372] The first data source is compatibility information, medical records, and other patient data 514 that has recently been processed to create additional utility during predictive analysis, such as Figure 11 The second data source is the same except that it contains additional historical processed data 551 that has been previously generated. These sources will serve as derivable data from which indicators and other mapping mechanisms can be found.

[0373] A third data source, containing a specific set of values ​​corresponding to each value within the second data source 551, is historical data 552 of actual implant performance and lifespan measures provided by previous patients. This is used as the ground truth and is predictable.

[0374] Predictions can be generated based on the first data source 514 by training and executing 553 various forms of machine learning, data science, and mathematical algorithms or methods. In certain embodiments, this will primarily consist of various supervised approaches. These types of approaches generally operate in two distinct phases, including a training phase and an execution phase.

[0375] The training phase involves the second data source 551 and the third data source 552, where each dataset in the second data source 551 is mapped to a specific set of values ​​in the second data source 552. This training phase involves identifying indicators in each dataset that partially or largely correspond to this mapping, such that if another dataset contains these same indicators, it is likely that this dataset will also have the same or similar corresponding values. Training continues until a mapping structure is formed that maps the parsed indicators to the values ​​they most commonly reference.

[0376] The execution phase involves only the first data source 514, which has no known corresponding values. This execution phase initially involves identifying the same indicators found in each dataset from this source during the training phase. These indicators are then fed into the previously created mapping structure to identify the values ​​they correspond to. These values ​​are then defined as the values ​​to which the initial dataset can correspond.

[0377] This training phase is typically performed using different segments of the data rather than the data as a whole. These segments can include training segments, test segments, and validation segments, where the data and corresponding values ​​are known for each segment. The training phase begins by generating a mapping structure corresponding only to the training segment. The data in the test segment is then passed through this mapping structure, where the returned values ​​are compared with the actual known values ​​for that segment. This provides a measure of accuracy based on how close the returned values ​​are to the actual values. If this accuracy is satisfactory (between 95-100% according to a specific embodiment), the test is performed again using the validation segment. This is to simulate its performance on real-world data, where, although the training and test segments have been seen before, the validation segment remains unknown. This ensures that the mapping structure performs well for all data, not just the test segment, a phenomenon known as overfitting.

[0378] Supervised algorithms or methods vary widely in their complexity and their predictive power, and using various types of supervised algorithms or methods simultaneously can also produce beneficial results beyond the comparison point. These algorithms or methods can include linear and polynomial regression, logistic regression, naive Bayesian networks, Bayesian networks, support vector machines, decision trees, random forests, k-nearest neighbor classifiers, and neural networks, which alternatively include other algorithms or methods as will be appreciated by those skilled in the art.

[0379] Other embodiments may use different prediction methods, including unsupervised, semi-supervised, and enhanced methods, as known to those skilled in the art. Unsupervised and semi-supervised algorithms or methods are provided with a data set and are made to extract meaning from that data set with little or no guidance as to what they are looking for. This allows for finding unknown information or connections in the data that may provide additional utility, depending on what they are and how consistent they are in other data sets.

[0380] Reinforcement algorithms or methods attempt to run a series of calculations with the goal of producing a specific value. These reinforcement algorithms or methods provide either a positive or negative stimulus, depending on how accurately the value compares to what it should be. When provided with a positive stimulus, these reinforcement algorithms or methods continue to perform the same calculations they have already completed and may perform other calculations similar to those. If provided with a negative stimulus, these reinforcement algorithms or methods may stop performing the current calculation and try a number of different calculations. A degree of randomness is often added to these algorithms to give them a starting point, which means that these reinforcement algorithms or methods may require more execution cycles to achieve a satisfactory result than existing predictive analysis methods.

[0381] Predictions 553 can be generated based on processed data 514 by running simulations involving different types of scenarios, events, and conditions that may affect the implant. These types of instances are likely to be simulated mathematically, with probability measures added to account for the currently uncertain situation.

[0382] In certain embodiments, the simulation will be designed around different types of implant degradation and the scenarios that these can take. Two main data sources will be provided.

[0383] The first source 514 will be processed data containing various information related to the quality of the implant therapy. This will be used to identify the types of problems that may be most prevalent, or the types of problems that the implant and related tissue are susceptible to.

[0384] The second source 552 would be information about the patient's lifestyle and other aspects, which could include the patient's activity level and the average amount of trauma their implants might experience as a result. This information would indicate the rate and extent of exacerbation of any problems that might be experienced, as well as the likelihood of physical trauma causing these problems.

[0385] Currently, simulation has been mentioned in the singular, but this may not be the case if additional benefits can be found by dividing the simulation into multiple separate simulations, each with its own purpose or prediction goal. Given the complexity typically involved, such division may be advantageous, at least from a development and production perspective.

[0386] Other embodiments may utilize different simulations, depending on their context and application. This is likely to depend on the form of implant, as therapies occurring in the human body will be affected differently depending on what tissue or body part they are replacing or strengthening.

[0387] The generated predictions are used to provide insights into the performance and longevity of the implant therapy 556. This type of information typically considers the impact of certain variables on the implant 557-558, or the correlation between certain variables and the implant status 559-560. In certain embodiments, this type of information is primarily based on orthopedic indicators that define when a particular implant is likely to have problems. This allows for appointments to be scheduled in advance, as well as for certain preventative measures to be taken during the procedure to produce a more favorable outcome.

[0388] The patient's lifestyle, in terms of their activity level, indicates how much trauma the implant will typically experience. By comparing this activity level, or any particularly high impact events, with the degradation rate determined based on the patient input, it is possible to predict 558 the impact of that trauma and how much it may worsen over a certain period of time.

[0389] Before implant therapy, the composition of the implant and the health of the tissue will be known to some extent. Problems between these two sets of information can be predicted by comparing them together with the lifespan of the implant and when the patient is likely to need revision surgery 559.

[0390] It can be assumed that the patient's physical condition, health status, and age have a strong correlation with the longevity of the implant 560. The types of situations and traumas to which the implant may be susceptible can be determined through this correlation. Based on this information and historical data of similar patients, a prediction can be made as to when a revision is considered necessary.

[0391] The morphology 561 of the tissue and implant determines the quality of the associated fit or connective joint that may exist between them. If the connective joint begins to degrade, the morphology will likely be an insightful indicator of the likely cause of degradation over time, especially when used in conjunction with predictions made about the health and composition of the implant and tissue 558. Comparing the morphology, and therefore indicators related to the quality of the connective joint, to the point at which revision surgery is considered necessary can predict when this point will occur.

[0392] Other prediction methods and outcome information may exist beyond those explicitly outlined herein 561. Prediction methods may not necessarily be performed only individually, they may also be performed simultaneously and subsequently 556 where there is reason to do so.

[0393] Figure 13 A detailed schematic diagram is shown depicting the generation of a set of tissue morphology corrective actions for a surgeon to consider implementing.

[0394] The starting point 604 of the process begins with an initial sampling 605 of a set of corrective actions that are ideal for changing the tissue morphology into optimal mechanical alignment.

[0395] The resulting set of sampled corrective actions 606 for perfect mechanical alignment may not be implemented for a variety of reasons, as will be detailed herein.

[0396] First, there may not be enough existing tissue to form a secure fit 500 that results in optimal implant performance and longevity predictions.

[0397] Additionally, the accuracy of the surgical resection tools being used may be below a threshold that allows accurate application of the corrective action set. For example, if the ideal tissue morphology is a thin slice at a slight angle, it may be beyond the surgeon's ability to use the available tools.

[0398] As discussed above, the resulting tissue morphology estimated by the surgeon is delivered to the simulated implant performance and life prediction 500 to provide result information 557 that can be used for comparison with other simulated action sets and the existing state of the tissue.

[0399] As detailed above, the simulated resulting tissue morphology result information 557 is evaluated 607 to determine whether the set of actions is desirable, and if so, one or more numerical quantities are calculated for use as comparison values.

[0400] The result information 557 should be compared 608 to the best corrective action set 610 (if any) simulated so far in the process. If the result information 557 compares to a better corrective action set, the sampled corrective action set 606 is stored 609 and replaces the best corrective action set 610.

[0401] The process will then consider 611 whether the current execution limit has been reached 611. This is a limit on some scarce resource, such as computing time, real time, energy, storage space, or cooling capacity.

[0402] If there are resources available to continue searching for a better set of corrective actions, then a relaxed set of corrective actions 605 will be sampled.

[0403] If resources are exhausted, the best corrective action set 610 is compared 612 to the result information 557 for the current state.

[0404] If the optimal corrective action set 610 is better than a predetermined threshold, then the optimal corrective action set is displayed to the surgeon 613 for consideration 613. After the surgeon has executed the corrective action set, this in turn can lead to another implant performance and lifespan prediction based on tissue state and morphology.

[0405] If the best set of corrective actions 610 is not better than a predetermined threshold, the process will alert the operator that an action threshold 614 has been reached, indicating that further substantial improvement is unlikely to be achieved.

[0406] The features presented herein can be performed electronically by any capable system or machine that can accomplish these features within any constraints imposed by its specific application. This can be performed online, offline, or in a capacity that relies on some combination of online and offline.

[0407] Data extracted or generated as a result of the features presented herein can be stored electronically. This can be done offline, online, or through some combination of both. This data can be accessed immediately or within a delayed timeframe for retrieval, processing, and any other form of use. All types of data can be stored, but some types of data can only be maintained intermittently.

[0408] It should be understood that the features presented herein and the various processes they encompass do not necessarily need to be performed in the order described, nor do they require a specific environment or situation. The order, nature, preparation, and execution of these features and processes may depend on a variety of circumstances, such as the medical application of the invention or method. One such circumstance may be the patient's condition and morphology, which may require additional processes or customization to coincide with any specific issues or constraints, as is common in medical practices such as orthopedics.

[0409] It will be appreciated by those skilled in the art that variations and modifications of the invention described herein will be apparent without departing from the spirit and scope of the invention. Variations and modifications apparent to those skilled in the art are deemed to fall within the broad scope and area of ​​the invention as set forth herein.

[0410] Future patent applications may be filed in Australia or overseas based on or claiming priority from this application. It should be understood that the following provisional claims are provided by way of example only and are not intended to limit the scope of protection that may be claimed in any such future application. Features may be added to or deleted from the provisional claims at a later date in order to further define or redefine one or more inventions.

[0411] like Figures 1 to 4 and Figures 11 to 13 The depicted methods 10, 100, 200, 300, 400, 500, and 600 (and associated sub-methods described herein) may be implemented using, for example, Figure 14 The computing device / computer system 1000 shown is implemented as follows, wherein Figures 1 to 13 The processes described herein can be implemented as software, such as one or more application programs executable within computing device 1000. Specifically, the steps of methods 10, 100, 200, 300, 400, 500, and 600 are implemented by instructions executed within the software within computer system 1000. These instructions can be implemented as one or more code modules, each of which is configured to perform one or more specific tasks. The software can also be divided into two distinct parts, with a first part and corresponding code modules performing the described methods, and a second part and corresponding code modules managing the user interface between the first part and a user. For example, the software can be stored on a computer-readable medium, including a storage device described below. The software is loaded from the computer-readable medium into computer system 1000 and then executed by computer system 1000. A computer-readable medium having such software or a computer program recorded thereon is a computer program product. The use of a computer program product within computer system 1000 advantageously implements a device for quality analysis of implant procedures and life expectancy of orthopedic implants in an intraoperative setting.

[0412] Reference Figure 14 , an exemplary computing device 1000 is shown. Exemplary computing device 1000 may include, but is not limited to, one or more central processing units (CPUs) 1001 including one or more processors 1002, a system memory 1003, and a system bus 1004 that couples various system components including system memory 1003 to processing unit 1001. System bus 1004 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures.

[0413] Typically, the computing device 1000 also includes computer-readable media, which may include any available media that the computing device 1000 can access, and includes volatile and non-volatile media and removable and non-removable media. By way of example and not limitation, computer-readable media may include computer storage media and communication media. Computer storage media include media implemented with any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage devices, cassettes, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by the computing device 1000. Typically, communication media implement computer-readable instructions, data structures, program modules or other data in a modulated data signal (such as a carrier wave or other transmission mechanism) and include any information transfer medium. By way of example and not limitation, communication media include wired media (such as a wired network or direct line connection) and wireless media (such as sound media, RF media, infrared media and other wireless media). Combinations of the any of the above should also be included within the scope of computer-readable media.

[0414] System memory 1003 includes computer storage media in the form of volatile and / or nonvolatile memory, such as read-only memory (ROM) 1005 and random access memory (RAM) 1006. A basic input / output system 1007 (BIOS), containing the basic routines that help to transfer information between elements within computing device 1000, such as during startup, is typically stored in ROM 1005. RAM 1006 typically contains data and / or program modules that are immediately accessible to and / or currently being operated on by processing unit 1001. By way of example, and not limitation, Figure 14 Operating system 1008 , other program modules 1009 , and program data 1010 are shown.

[0415] The computing device 1000 may also include other removable / non-removable, volatile / non-volatile computer storage media. By way of example only, Figure 14 A hard drive 1011 is shown that reads from or writes to a non-removable, non-volatile magnetic medium. Other removable / non-removable, volatile / non-volatile computer storage media that can be used with the exemplary computing device include, but are not limited to, magnetic tape cassettes, flash memory cards, digital versatile disks, digital video tapes, solid-state RAM, solid-state ROM, and the like. Hard drive 1011 is typically connected to system bus 1004 via a non-removable memory interface, such as interface 1012.

[0416] As discussed above and in Figure 14 The drives and their associated computer storage media shown in FIG. 1 provide storage of computer-readable instructions, data structures, program modules and other data for the computing device 1000. Figure 14 10, for example, hard disk drive 1011 is shown as storing operating system 10YY, other program modules 1014, and program data 1015. It should be noted that these components may be the same as or different from operating system 1008, other program modules 1009, and program data 1010. Operating system 1013, other program modules 1014, and program data 1015 are labeled with different numbers to minimally indicate that they are different versions.

[0417] The computing device also includes one or more input / output (I / O) interfaces 1030 connected to the system bus 1004, including an audio-video interface coupled to output devices including one or more of a video display 1034 and speakers 1035. The input / output interface(s) 1030 are also coupled to one or more input devices including, for example, a mouse 1031, a keyboard 1032, or a touch-sensitive device 1033, such as a smartphone or tablet device.

[0418] In connection with the following description, the computing device 1000 can operate in a networked environment using logical connections to one or more remote computers. Figure 14 Computing device 1000 is shown connected to a network 1020, which is not limited to any particular network or networking protocol, but may include, for example, Ethernet, Bluetooth, or IEEE 802.X wireless protocols. Figure 141021. The logical connection depicted in FIG1021 is a general network connection 1021, which can be a local area network (LAN), a wide area network (WAN), or other network, such as the Internet. The computing device 1000 is connected to the general network connection 1021 through a network interface or adapter 1022, which is in turn connected to the system bus 1004. In a networked environment, program modules depicted with respect to the computing device 1000, or a portion or peripheral of the computing device, can be stored in the memory of one or more other computing devices that are communicatively coupled to the computing device 1000 via the general network connection 1021. It should be understood that the network connections shown are exemplary and that other means of establishing a communications link between computing devices can be used.

[0419] explain

[0420] bus

[0421] In the context of this document, the term "bus" and its derivatives, although described in the preferred embodiment as a communication bus subsystem for interconnecting devices, including through parallel connections such as Industry Standard Architecture (ISA), conventional Peripheral Component Interconnect (PCI), or through serial connections such as PCI Express (PCIe), Serial Advanced Technology Attachment (Serial ATA), should be broadly interpreted in this document to mean any system for transmitting data.

[0422] according to

[0423] As described herein, "according to" may also mean "as a function of," and is not necessarily limited to integers specified therein.

[0424] Component

[0425] As described herein, a "computer-implemented method" does not necessarily infer execution by a single computing device, such that steps of the method may be performed by more than one cooperating computing devices.

[0426] Similarly, objects as used herein, such as "web server," "server," "client computing device," "computer-readable medium," etc., need not necessarily be construed as a single object, but may be implemented as two or more cooperating objects, e.g., a web server being construed as two or more web servers in a server group working together to achieve a desired goal, or computer-readable media being distributed in a combined manner, such as program code being provided on a compact disk that is activated by a license key that is downloadable from a computer network.

[0427] database

[0428] In the context of this document, the terms "data source" and "database" are interchangeable, and derivatives of these terms may be used to describe a single database, a collection of databases, a database system, and the like. A database system may include a collection of databases, where the collection of databases may be stored on a single embodiment or across multiple embodiments. The term "database" is also not limited to referring to a particular database format, but may refer to any database format. For example, database formats may include MySQL, MySQLi, XML, and the like.

[0429] process

[0430] Unless otherwise specifically stated, as will become clear from the following discussion, it should be understood that throughout this specification, discussions using terms such as "process," "calculate," "calculate," "determine," "analyze," etc. refer to the actions and / or processes of a computer or computing system or similar electronic computing device that manipulate and / or transform data represented as physical (e.g., electronic) quantities into other data similarly represented as physical quantities.

[0431] processor

[0432] In a similar manner, the term "processor" may refer to any device or portion of a device that processes electronic data, for example, from registers and / or memory, to transform that electronic data into other electronic data, for example, that may be stored in registers and / or memory. A "computer" or "computing device" or "computing machine" or "computing platform" may include one or more processors.

[0433] In one embodiment, the methods described herein can be performed by one or more processors that receive computer-readable (also referred to as machine-readable) code, the computer-readable code comprising an instruction set that, when executed by the one or more processors, performs at least one of the methods described herein. Any processor capable of executing an instruction set (sequential or otherwise) that specifies an action to be taken is included. Thus, an example is a typical processing system that includes one or more processors. The processing system may further include a memory subsystem that includes main RAM and / or static RAM, and / or ROM.

[0434] Computer readable media

[0435] Furthermore, the computer-readable carrier medium may form or be comprised in a computer program product. A computer program product may be stored on a computer-usable carrier medium, the computer program product comprising computer-readable program means for causing a processor to perform the methods described herein.

[0436] Networked or multiple processors

[0437] In alternative embodiments, the one or more processors may operate as a standalone device or may be connected (e.g., networked) to other processor(s). In a networked deployment, the one or more processors may operate as a server or client computer in a server-client network environment, or as a peer machine in a peer-to-peer or distributed network environment. The one or more processors may form a web appliance, a network router, a switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions for the machine to take.

[0438] It should be noted that although certain (certain) figures show only a single processor and a single memory carrying computer readable code, those skilled in the art will understand that this includes many of the aforementioned components, but they are not explicitly shown or described in order not to obscure the innovative aspects of the present invention. For example, although only a single machine is shown, the term "machine" should also be taken to include any collection of machines that individually or jointly execute an instruction set (or multiple instruction sets) to perform any one or more of the methodologies discussed herein.

[0439] Implementation Method

[0440] It should be understood that, in one embodiment, the steps of the method discussed are performed by a suitable processor (or processors) of a processing (i.e., computer) system executing instructions (computer-readable code) stored in a storage device. It should also be understood that the present invention is not limited to any particular implementation or programming technique, and that any suitable technique for implementing the functionality described herein can be used to implement the present invention. The present invention is not limited to any particular programming language or operating system.

[0441] Device for performing a method or function

[0442] In addition, some embodiments are described herein as methods or combinations of methods that can be implemented by a processor or processor device, a computer system, or other devices that perform functions. Thus, a processor having the necessary instructions for performing such a method or method elements forms a device for performing such a method or method elements. In addition, the elements described herein of the apparatus embodiments are examples of devices for performing the functions performed by the elements for the purpose of performing the present invention.

[0443] Example

[0444] References throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases "in one embodiment" or "in an embodiment" throughout this specification are not necessarily all referring to the same embodiment, but may do so. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments, as will be apparent to one of ordinary skill in the art from this disclosure.

[0445] Similarly, it should be understood that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment / arrangement, drawing, or description thereof in order to simplify the disclosure and aid in understanding one or more of the various innovative aspects. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, innovative aspects lie in fewer features than all the features of a single preceding disclosed embodiment. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment / arrangement of the invention.

[0446] In addition, although some embodiments described herein include some features included in other embodiments but not other features, as will be appreciated by those skilled in the art, combinations of features from different embodiments are intended to be within the scope of the invention and to form different embodiments / arrangements. For example, in the appended claims, any of the claimed embodiments may be used in any combination.

[0447] Additional Examples

[0448] Thus, one embodiment of each method described herein is in the form of a computer-readable carrier medium carrying an instruction set, such as a computer program for execution on one or more processors. Thus, as will be appreciated by those skilled in the art, embodiments of the present invention may be embodied as methods, devices such as special-purpose devices, devices such as data processing systems, or computer-readable carrier media. A computer-readable carrier medium carries computer-readable code comprising an instruction set that, when executed on one or more processors, causes the one or more processors to implement the method. Thus, various aspects of the present invention may take the form of a method, a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a carrier medium (e.g., a computer program product on a computer-readable storage medium) carrying a computer-readable program code embodied in the medium.

[0449] Specific details

[0450] In the description provided herein, numerous specific details are set forth. However, it should be understood that embodiments of the present invention may be practiced without these specific details. In other instances, well-known methods, structures, and techniques have not been shown in detail in order to avoid obscuring the understanding of this specification.

[0451] the term

[0452] In describing the embodiments of the present invention shown in the accompanying drawings, specific terminology will be employed for the sake of clarity. However, the present invention is not intended to be limited to the specific terminology so selected, and it should be understood that each specific term includes all technical equivalents that operate in a similar manner to achieve a similar technical purpose. Terms such as "forward," "rearward," "radially," "circumferentially," "upward," and "downward" are used as expedient words to provide a reference point and should not be construed as limiting terms.

[0453] Different instances of an object

[0454] As used herein, unless otherwise indicated, the use of ordinal adjectives "first," "second," "third," etc. to describe the same object merely indicates that different instances of similar objects are mentioned and is not intended to imply that the objects so described must be in a given order, whether in time, space, rank, or in any other manner.

[0455] Scope of the Invention

[0456] Thus, while there has been described what are considered to be preferred arrangements of the present invention, those skilled in the art will recognize that other and further modifications may be made to these preferred arrangements without departing from the spirit of the present invention, and it is intended that all such changes and modifications that fall within the scope of the present invention be claimed. Functionality may be added or deleted from the block diagrams, and operations may be interchanged between functional blocks. Steps may be added or deleted from the described methods within the scope of the present invention.

[0457] Although the invention has been described with reference to specific examples, it will be appreciated by those skilled in the art that the invention may be embodied in many other forms.

[0458] Industrial Applicability

[0459] It will be clear from the above that the described arrangement is applicable to the mobile device industry, in particular to methods and systems for distributing digital media via mobile devices.

[0460] It will be appreciated that the methods / devices / apparatuses / systems described / illustrated above at least generally provide methods and systems for quality analysis of implantation procedures and prediction of lifespan of orthopedic implants in an intraoperative environment.

[0461] The systems and methods described herein and / or shown in the accompanying drawings are presented by way of example only and do not limit the scope of the invention. Unless otherwise specifically stated, various aspects and components of the systems and methods may be modified or may have been replaced with known equivalents or as yet unknown alternatives, such as those that may be developed in the future or that may be deemed acceptable in the future. Because the potential range of applications is large, and because the systems and methods of the present invention are intended to be adaptable to many such variations, the systems and methods may be modified for various applications without exceeding the scope and spirit of the claimed invention.

Claims

1. A system for supporting surgical bioimplant therapy by integrating an implant with a patient's tissue, comprising: one or more sensors for sensing a state attribute of tissue and a morphological attribute of tissue of the patient during a surgical procedure to collect at least state data and morphological data to generate collected data, wherein the state attribute of tissue comprises one or more of composition, hydration, density, necrosis, staining, reflectance, thermal consistency, deterioration, or particle dissolution, wherein the one or more sensors are included in a surgical environment in which the surgical procedure is being performed; and One or more processors, adapted to: preprocessing the collected data during the surgical procedure to generate processed data, the processed data having a form suitable for interpretation, wherein the preprocessing includes modifying the collected data to remove data dimensionality; interpreting the processed data to extract data representative of the structure of the patient's tissue and data representative of the implant during the surgical procedure; determining compatibility data describing a simulated fit between the data representation of the structure of the patient's tissue and the data representation of the implant during the surgical procedure to determine compatibility of a connecting surface of the implant with a state of a receiving surface of the patient's tissue; using the compatibility data to predict at least one of a lifespan or performance of the implant during the surgical procedure; generating and displaying, via a display device, a visualization depicting the simulated fit during the surgical procedure, wherein the visualization is generated based on the collected data collected by the one or more sensors; generating corrective action data for modifying a receiving surface of tissue of the patient during the surgical procedure to improve prediction of the life or performance of the implant; receiving, during the surgical procedure, additional data describing the physical fit between the patient's tissue and the implant via the one or more sensors; comparing the simulated fit depicted in the visualization with i) the physical fit and ii) corrective motion data during the surgical procedure; responsive to the comparison of the simulated fit and during the surgical procedure, modifying the corrective motion data; and During the surgical procedure, the display device is configured to provide modified corrective action data.

2. The system of claim 1, wherein: The tissue includes biological tissue.

3. The system of claim 1, wherein: The implant comprises a knee joint prosthesis or a hip joint prosthesis.

4. The system of claim 1, wherein: The implant includes one or more features including threads or patterns on one or more surfaces to at least one of promote osseointegration or increase rigidity of fixation to the tissue.

5. The system according to any one of claims 1 to 4, wherein: The one or more sensors may exist independently or as part of a sensor system or sensor group.

6. The system of claim 1, wherein: The one or more sensors include at least one sensor that is completely self-contained.

7. The system of claim 1, wherein: The one or more sensors include at least one sensor that requires at least one of an additional device, service, condition, or platform to be properly interfaced, configured, or operated.

8. The system of claim 1, wherein: The one or more sensors include at least one sensor individually configured to monitor, sense, collect, and provide data based on various characteristics, features, events, or measurements of an object.

9. The system of claim 8, wherein: The object includes one or more of the tissue, the implant, a connecting joint between the tissue and the implant, the surrounding environment, or a result of an action or interaction.

10. The system of claim 9, wherein: The object is processed to affect its original, initial or current state for at least one of preservation, identification, unification and fixation.

11. The system of claim 9, wherein: The object is structurally and / or chemically modified, which modifications are capable of changing the form of the object as part of or independent of any intraoperative therapeutic and / or surgical procedure.

12. The system of claim 1, wherein: The one or more sensors are configured to operate in an automated manner, by manual triggering, or any combination or sequence of manual and automatic triggering.

13. The system of claim 12, wherein: Manual triggering includes manual triggers including buttons, voice commands, gesture controls, or other physical actuations.

14. The system of claim 1, wherein: The one or more sensors are configured to at least one of sense indefinitely, sense periodically, and sense once while being influenced by at least one of a situation, an environment, a user control, and a sensor configuration.

15. The system of claim 14, wherein: The sensing is configured to operate in real time or near real time through some form of delayed processing, which can be affected by at least one of situation, environment, user control, and sensor configuration.

16. The system of claim 1, wherein: At least one of the one or more sensors requires external intervention, the external intervention comprising at least one of a change in position, angle, vicinity, proximity, configuration, lighting, or timing of the sensor.

17. The system of claim 1, wherein: The system collects data from a data source including at least one of a record, a file, a database, and a system.

18. The system of claim 1, wherein: The state attribute of the tissue includes at least one of composition, hydration, density, necrosis, coloration, reflectance, or temperature.

19. The system of claim 1, wherein: The one or more sensors are used to sense a status attribute of the implant during a surgical procedure, wherein the status attribute of the implant comprises at least one of composition, deterioration, density, or particle dissolution.

20. The system of claim 1, wherein: The one or more sensors are used to sense morphological properties of the implant during surgery, each of the morphological properties of the tissue and the morphological properties of the implant including one or more of shape, flatness, parallelism, roughness, waviness, peak distribution, porosity or stiffness.

21. The system of claim 1 , wherein the one or more processors determine a tissue state, an implant state, a tissue morphology, and an implant morphology based on the collected data, and pre-process the collected data before determining the tissue state, the implant state, the tissue morphology, and the implant morphology, wherein: Preprocessing the collected data includes at least one of the following operations: removing any noisy, erroneous or redundant data from said collected data; formatting the collected data, flattening the collected data, or extracting the collected data from a storage device; sampling the collected data; scaling or aligning the collected data so that values ​​of the collected data are within a comparable range; Decomposing the collected data so as to separate representative or specific features or parts of the collected data into constituent elements; or The collected data is aggregated so that individual features, constituent elements, segments or portions of the collected data can be combined into a single entity.

22. The system of claim 20, wherein: The pre-processing of the collected data includes cleaning the data, including at least one of removing or repairing any noisy, erroneous, or redundant data.

23. The system of claim 20, wherein: The pre-processing of the collected data includes formatting the data, which includes rearranging the data into a more appropriate structure or form, flattening the data, or extracting the data from its current storage device.

24. The system of claim 20, wherein: The pre-processing of the collected data includes sampling the data, and the sampling includes selecting or partitioning a portion of the data.

25. The system of claim 20, wherein: The pre-processing of the collected data includes scaling or alignment of the data so that the values ​​of the data are within a comparable range or achieve some additional level of comparability.

26. The system of claim 20, wherein: The pre-processing of the collected data includes decomposition of the data so that representative or other specific features or parts of the data can be separated into constituent elements or elements that provide more utility individually.

27. The system of claim 20, wherein: The pre-processing of the collected data includes aggregation of the data so that individual features, constituent elements, segments or parts of the data can be combined into a single entity.

28. The system of claim 20, wherein: The pre-processing of the collected data includes at least one work action related to at least one of a process, an operation, a generation, and a modification.

29. The system of claim 20, wherein: The system includes an additional entity, and if the additional entity has separately or independently performed the interpretation of the processed data, the interpretation of the processed data is not performed or is partially performed.

30. The system of claim 21, wherein: Determining the tissue state, the tissue morphology, the implant state, and the implant morphology includes interpretation of the processed collected data.

31. The system of claim 30, wherein: Interpretation of the processed data includes at least one working action related to at least one of any general or specific mathematical equation, theory, calculation, concept.

32. The system of claim 30, wherein: The interpretation of the processed data includes at least one work action associated with the performance of a process or function that calculates at least one of a customized or standardized geometric measure, a morphological measure, a structural measure.

33. The system of claim 30, wherein: The interpretation of the processed collected data includes the execution of machine learning, data science, or mathematical methods.

34. The system of claim 30, wherein: The interpretation of the processed collected data is performed by at least one of a sensor controller or a bridge device.

35. The system of claim 30, wherein: The interpretation of the processed collected data is based on observations or default conclusions provided by validated personnel.

36. The system of claim 30, wherein: The explanation is explicitly provided through at least one of medical records or history and preoperative therapy.

37. The system of claim 30, wherein: The interpretation of the processed data includes at least one work action related to at least one of process, equalize, generate, and modify.

38. The system of claim 1, wherein: Generating compatibility data based on interpreted data from the tissue including a receiving surface, an associated implant including an engagement surface, and a joint between the receiving surface and the engagement surface, and generating the compatibility data comprises the following steps: generating a degree of compatibility of the engagement portion with either or both of the receiving surface and the engagement surface; Analyze the effects of implant insertion or fixation; Assessing implant fit; and The lifespan and performance of the implant are predicted.

39. The system of claim 38, wherein: The one or more processors determine a tissue state, an implant state, a tissue morphology, and an implant morphology based on the collected data, wherein generating the compatibility level includes comparing the tissue state and the implant state, and comparing the tissue morphology and the implant morphology.

40. The system of claim 39, wherein: Comparing the tissue state and the implant state includes determining compatibility of the tissue state and the implant state.

41. The system of claim 40, wherein: Determining the compatibility of the tissue state and the implant state includes determining whether the implant material is compatible with the tissue.

42. The system of claim 41, wherein: The suitability of the implant material includes the potential for adverse reactions to occur at any time and for any duration, including intraoperatively or postoperatively.

43. The system of claim 41, wherein: The suitability of the implant material includes at least one of an intended or possible fixation material and process.

44. The system of claim 41, wherein: The suitability of the implant material includes at least one of possible stress, pressure, and intended usage scenario.

45. The system of claim 40, wherein: Determining the compatibility of the tissue state and the implant state includes examining the health of the tissue to measure fixation potential and viability.

46. ​​The system of claim 39, wherein: Comparing the tissue morphology and the implant morphology includes determining the compatibility of the tissue morphology and the implant morphology.

47. The system of claim 46, wherein: Determining the compatibility of the tissue morphology and the implant morphology includes determining whether the shape and morphology of the tissue will enable insertion of the implant.

48. The system of claim 46, wherein: Determining the compatibility of the tissue morphology and the implant morphology includes determining the extent of contact made by the implant against the tissue upon insertion.

49. The system of claim 46, wherein: Determining the compatibility of the tissue morphology and the implant morphology includes determining the extent to which the surface of the tissue fills the threads of the implant and the extent to which the distribution pattern of the tissue is comparable within the compared threads.

50. The system of claim 38, wherein: Analyzing the effects of implant insertion or fixation includes determining the likely effects that inserting the implant will have on the tissue or the implant.

51. The system of claim 50, wherein: Effects of insertion of the implant on the tissue may include surface disruption and / or density reduction.

52. The system of claim 38, wherein: The effect of the insertion of the implant on the tissue includes the distribution or effect of any applied fixatives, either singly or in combination, which can be present directly or indirectly.

53. The system of claim 38, wherein: Assessing implant fit includes comparing the current placement of the implant to a calculated ideal placement.

54. The system of claim 53, wherein: The placement of the implant on the tissue is defined by at least one of the following factors: the degree of contact between the tissue and the implant, the fill and pattern of tissue within the implant threads, or the stress distribution on the implant.

55. The system of claim 53, wherein: The ideal layout is defined by beneficial or advantageous values ​​describing properties or characteristics of the implant layout.

56. The system of claim 39, wherein: The quality of the implant fit is influenced by the implant state, the implant morphology, the tissue state and the tissue morphology, the situation and environment, the intended use scenario and the stresses to which the implant will be subjected.

57. The system of claim 38, wherein: The results of the assessment are ambiguous and provide a quantitative or qualitative measure based on all available information appropriate to allow an informed decision.

58. The system of claim 56, wherein: At least one of a suggestion, a comment, an indicator, and a hint is used to inform the entity about necessary changes needed to bring the current location closer to the calculated ideal location.

59. The system of claim 1, comprising performing additional analysis if the implant is at least one of repositioned, moved, and rotated.

60. The system of claim 38, wherein: Predicting the life and performance of the implant includes at least one working action, which is related to at least one of the generated compatibility data, the state and morphology of the tissue and implant, the fixation method, the previous medical history or record, the expected usage and the implant stress level.

61. The system of claim 38, wherein: The lifespan and performance of the implant include both quantitative measures of time and qualitative measures related to how easily the patient can perform certain tasks.

62. The system of claim 38, wherein: The generated implant life and performance information is used directly or interpreted to generate recommendations based on the patient's usage or current lifestyle.

63. The system of claim 38, wherein: Predicting the life and performance of an implant comprises at least one work action related to the execution of a machine learning, data science or mathematical concept, model, equation, or any combination thereof in any order.

64. The system of claim 59, wherein: The use of at least one simulated computing system or entity to predict, generate, calculate, verify, validate, or any combination thereof in any order.

65. The system of any one of claims 1 and 59, wherein The processing of the compatibility data comprises at least one work action associated with converting said compatibility data into an evaluable form.

66. The system of claim 65, wherein: The conversion of the compatibility data comprises at least one working action involving single, multiple, combined or sequential pre-processing steps.

67. The system of claim 65, further comprising a pre-processing step, the pre-processing step comprising cleaning the data, the cleaning comprising removing or repairing any noisy, erroneous or redundant data.

68. The system of claim 66, wherein: The pre-processing step includes formatting the data, which may include rearranging the data into a more suitable structure or form, flattening the data, or extracting it from its current storage device.

69. The system of claim 66, wherein: The pre-processing step comprises sampling the data, which comprises selecting or partitioning a portion of the data.

70. The system of claim 65, wherein: The conversion of the compatibility data includes at least one work action, and the at least one work action involves a single, multiple, combined or sequential raw data operation or a pre-processed data operation.

71. The system of claim 70, wherein: The manipulation of the raw data or the pre-processed data includes scaling or alignment of the data so that the values ​​of the data are within a comparable range or achieve some additional level of comparability.

72. The system of claim 70, wherein: Manipulation of the raw or pre-processed data includes decomposition of the data to separate representative or other specific features or portions of the data into constituent elements or elements that provide more utility than when used alone.

73. The system of claim 70, wherein: The manipulation of the raw or pre-processed data includes aggregation of the data to combine separate features, constituent elements, segments or portions of the data into a single entity.

74. The system of claim 65, wherein: The conversion of the compatibility data includes at least one work action related to at least one of a process, manipulation, generation and modification adapted to prepare the data for use or evaluation.

75. The system of claim 1, wherein: The system includes a comparator including a comparison information data set in a comparable form.

76. The system of claim 1, further comprising receiving post-operative results from the patient a certain period of time after the surgery has occurred.

77. The system of claim 1, wherein: Means for generating predictions of post-operative implant performance include training machine learning, data science, or mathematical models to provide performance predictions.

78. The system of claim 77, wherein: Any machine learning, data science, or mathematical concept, model, equation, or combination of them in any order is augmented by the introduction of new data.

79. The system of claim 1, wherein: Generating correction information for modifying the morphology of the tissue and providing the generated correction information including a set of actions is suitable for enabling a surgeon to improve the life and performance of the implant.

80. The system of claim 79, wherein The correction information includes a sample of a set of possible actions that differ from the predicted post-operative implant performance.

81. The system of claim 79, wherein: The correction information includes numerical quantification of the lifespan and performance of the implant for currently existing and subsequently generated tissue morphology after the proposed set of actions has been performed.

82. The system of claim 79, wherein: The correction information includes pre-configured thresholds above which corrective action is identified as not feasible given the surgical cutting technique being applied and its inherent inaccuracies.

83. The system of claim 70, wherein: At least one of the collected data, the raw data, the processed data, the manipulated raw data, the manipulated processed data, the interpreted processed data, the usable data, and the evaluable data is stored electronically, including offline, online, or a combination of offline and online, for later retrieval and / or processing.

84. The system of claim 70, wherein: Any at least one work action is influenced, affected, adjusted, or directed by a patient-specific deformation or problem, wherein the patient-specific deformation or problem includes one or more of the following: valgus or varus error, mechanical alignment error, or error that accommodates the patient's anatomy that differs from what is considered normal or ideal.

85. The system of claim 70, wherein: The at least one working action occurs in an intraoperative environment.

86. The system of claim 85, wherein: The at least one working action occurs in the same, different, or alternating sequences and is adapted to produce the same, similar, or different end results.

87. The system of claim 86, wherein: The at least one work action occurs in real time or in near real time via a delay processing procedure.

88. The system of claim 83, wherein: The required data processing or data storage takes place internally or externally at a centralized online entity or decentralized online entities.

89. The system of claim 1, wherein: The one or more sensors include at least one of a Raman spectroscopy sensor, an optical imaging sensor, a thermal imaging sensor, a fluorescence spectroscopy sensor, a microscopy sensor, an acoustic sensor, a 3D metrology sensor, an optical coherence tomography sensor, a position sensor, a motion sensor, or a balance sensor.

90. The system of claim 89, wherein: The one or more sensors are adapted to sense properties of the state and / or morphology of the patient's tissue and / or the implant.

91. The system of claim 1, wherein the morphological properties include one or more of shape, flatness, parallelism, roughness, waviness, peak distribution, porosity, or stiffness.

92. The system of claim 1, further comprising outputting predictions of the lifespan and performance of the implant.

93. The system of any one of claims 1 and 90 to 92, further comprising outputting the generated correction data for modifying the receiving surface of the patient's tissue to improve prediction of the life and performance of the implant.

94. The system of claim 1, wherein: The collected data further includes historical data, wherein the historical data includes at least one of historical surgical procedure record data or historical patient data.

95. The system of claim 1, wherein: The pre-processing of the collected data includes one or more of the following: removing noisy, erroneous or redundant data; formatting the data into an appropriate data format; sampling the collected data into one or more representative segments; The data is scaled or aligned; the data is decomposed into component elements; or the data is aggregated to create a statistically meaningful data structure.

96. The system of claim 29, wherein: The additional entity includes a sensor controller or a bridge device.

97. A non-transitory computer-readable medium having instructions stored thereon, the instructions, when executed by a processor, causing the processor to perform operations for intraoperative implant fit analysis and lifespan prediction of a prosthetic implant to be integrated with a patient's physiology, the operations comprising: collecting data during a surgical procedure via a plurality of sensors located proximate to tissue and an implant and via a plurality of data sources, wherein the plurality of sensors are included in a surgical environment in which the surgical procedure is being performed; During the surgical procedure, modifying the collected data to remove data dimensionality; determining, during said surgical procedure, tissue status, implant status, tissue morphology, and implant morphology based on said collected data; During the surgical procedure, generating compatibility information between the tissue and the implant for describing a simulated fit based on the tissue state, the implant state, the tissue morphology, and the implant morphology; processing said compatibility information into a form suitable for evaluation against a predetermined comparator during said surgical procedure; generating and displaying, via a display device, a visualization depicting the simulated fit, wherein the visualization is generated based on data collected via the plurality of sensors; During the surgical procedure, generating and providing a set of corrective actions for modifying the tissue state and the tissue morphology to improve postoperative implant performance and longevity; wherein the tissue state comprises at least one of composition, hydration, density, necrosis, coloration, reflectance, or temperature; receiving, during the surgical procedure, additional data describing the physical fit between the tissue and the implant via the plurality of sensors; comparing the simulated fit depicted in the visualization to i) the physical fit and ii) the set of corrective actions during the surgical procedure; During the surgical procedure, modifying the set of corrective actions in response to the comparison of the simulated fit; and During the surgical procedure, the display device is configured to provide a revised set of corrective actions.

98. The non-transitory computer readable medium of claim 97 having additional instructions stored thereon that cause the processor to process the collected data prior to determining the tissue state, the implant state, the tissue morphology, and the implant morphology to obtain processed data, wherein Processing the collected data includes at least one of the following operations: removing any noisy, erroneous or redundant data from said collected data; formatting the collected data, flattening the collected data, or extracting the collected data from a storage device; sampling the collected data; scaling or aligning the collected data so that values ​​of the collected data are within a comparable range; Decomposing the collected data so as to separate representative or specific features or parts of the collected data into constituent elements; or The collected data is aggregated so that individual features, constituent elements, segments or portions of the collected data can be combined into a single entity.

99. The non-transitory computer-readable medium of claim 98, wherein determining the tissue state, the tissue morphology, the implant state, and the implant morphology comprises interpreting the processed data using a machine learning model to obtain interpreted data.

100. The non-transitory computer readable medium of claim 99, wherein: Generating the compatibility information based on the interpreted data from the tissue including the receiving surface, the associated implant including the engaging surface, and the joint between the receiving surface and the engaging surface, and generating the compatibility information includes the following operations: generating a degree of compatibility of the engagement portion with either or both of the receiving surface and the engagement surface; Analyze the effects of implant insertion or fixation; evaluating the implant fit; and The lifespan and performance of the implant are predicted.

101. The non-transitory computer readable medium of claim 100, wherein: Generating the degree of compatibility includes comparing the tissue state to the implant state, and comparing the tissue morphology to the implant morphology.

102. The non-transitory computer-readable medium of claim 97, wherein the operations further comprise training a machine learning model to provide performance predictions.

Images