Patient-Specific Medical Procedures, Devices, and Related Systems and Methods

Abstract

This document discloses systems and methods for designing and implementing patient-specific surgical procedures and / or medical devices. [Solution] In some embodiments, the method includes the step of receiving a patient dataset of a patient. The patient dataset is compared with a plurality of reference patient datasets, each of which is associated with a corresponding reference patient. A subset of the plurality of reference patient datasets is selected based at least partially on similarity to the patient dataset and the treatment outcomes of the corresponding reference patients. Based on the selected subset, at least one surgical procedure or medical device design for treating the patient is generated.

Description

Technical Field

[0001] [Cross-Reference to Related Applications] The present application claims priority to U.S. Non-Provisional Patent Application No. 16 / 735,222 filed on January 6, 2020 and No. 17 / 124,822 filed on December 17, 2020, the disclosures of which are incorporated herein by reference in their entireties.

[0002] The present disclosure generally relates to the design and implementation of medical care, and more specifically to systems and methods for designing and implementing surgical procedures and / or medical devices.

Background Art

[0003] Many types of data associated with patient treatment and surgical intervention are available. To determine a treatment protocol for a patient, physicians often rely on a subset of available patient data through the patient's medical records and historical outcome data. However, the amount of available patient data and historical data may be limited, and the available data may not correlate with or be relevant to the specific patient to be treated. In addition, although digital data collection and processing power have improved, technologies for determining optimal treatment protocols using collected data have lagged behind. For example, conventional techniques in the field of orthopedics may lack the ability to leverage large datasets to generate and optimize patient-specific treatments (e.g., surgical intervention and / or implant design) to achieve favorable treatment outcomes.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

[0005] The accompanying drawings illustrate various embodiments of the systems, methods, and various other embodiments of the disclosure of the present invention. Those skilled in the art will recognize that the element boundaries shown in the drawings (e.g., boxes, groups of boxes, or other shapes) represent examples of boundaries. In some examples, one element may be designed as multiple elements, or multiple elements may be designed as one element. In some examples, an element shown as an internal component of one element may be implemented as an external component in another example, and vice versa. Furthermore, elements may not be drawn to scale. Non-limiting and non-exclusive descriptions are illustrated with reference to the following drawings. Components in the drawings may not necessarily be to scale, emphasizing that they illustrate the principle instead. [Brief explanation of the drawing]

[0006] [Figure 1]This is a network connection diagram illustrating a system for providing patient-specific medical care according to the embodiment. [Figure 2] This figure shows computer devices suitable for use with the system shown in Figure 1, according to the embodiment. [Figure 3] This flowchart illustrates a method for providing patient-specific medical care according to the embodiment. [Figure 4A] This figure shows an exemplary dataset that can be used and / or generated in conjunction with the methods described herein, and is a patient dataset. [Figure 4B] This figure shows exemplary datasets that can be used and / or generated in conjunction with the methods described herein, depending on the embodiment, and includes multiple reference patient datasets. [Figure 4C] Figure 4B shows exemplary datasets that can be used and / or generated in conjunction with the methods described herein, along with similarity scores and outcome scores to the reference patient dataset. [Figure 5] This flowchart illustrates another method of providing patient-specific medical care through an embodiment. [Figure 6] This is a partial schematic diagram of a surgical environment and associated computer system for providing patient-specific medical care according to an embodiment. [Figure 7A] This figure shows an exemplary patient dataset that may be used and / or generated in conjunction with the methods described herein, depending on the embodiment. [Figure 7B] This figure shows an exemplary patient dataset that may be used and / or generated in conjunction with the methods described herein, depending on the embodiment. [Figure 7C] This figure shows an exemplary patient dataset that may be used and / or generated in conjunction with the methods described herein, depending on the embodiment. [Figure 7D] This figure shows an exemplary patient dataset that may be used and / or generated in conjunction with the methods described herein, depending on the embodiment. [Figure 8A]FIG. 1 is a diagram illustrating an exemplary virtual model of a patient's spine that can be used with and / or generated in accordance with the methods described herein according to embodiments. [Figure 8B] FIG. 2 is a diagram illustrating an exemplary virtual model of a patient's spine that can be used with and / or generated in accordance with the methods described herein according to embodiments. [Figure 9A-1] FIG. 3 shows an exemplary virtual model of a patient's spine in a preoperative anatomical configuration and a corrected anatomical configuration, and more specifically, is a diagram illustrating the preoperative anatomical configuration of the patient. [Figure 9A-2] FIG. 4 shows an exemplary virtual model of a patient's spine in a preoperative anatomical configuration and a corrected anatomical configuration, and more specifically, is a diagram illustrating the preoperative anatomical configuration of the patient. [Figure 9B-1] FIG. 5 shows an exemplary virtual model of a patient's spine in a preoperative anatomical configuration and a corrected anatomical configuration, and more specifically, is a diagram illustrating the corrected anatomical configuration. [Figure 9B-2] FIG. 6 shows an exemplary virtual model of a patient's spine in a preoperative anatomical configuration and a corrected anatomical configuration, and more specifically, is a diagram illustrating the corrected anatomical configuration. [Figure 10] FIG. 7 is a diagram illustrating an exemplary surgical plan for a patient-specific surgical procedure that can be used with and / or generated in accordance with the methods described herein according to embodiments. [Figure 11-1] FIG. 8 is a diagram illustrating an exemplary surgical plan report that details the surgical plan shown in FIG. 10 for surgeon review according to embodiments, and that can be used with and / or generated in accordance with the methods described herein. [Figure 11-2] FIG. 9 is a diagram illustrating an exemplary surgical plan report that details the surgical plan shown in FIG. 10 for surgeon review according to embodiments, and that can be used with and / or generated in accordance with the methods described herein. [Figure 12A] FIG. 10 is a diagram illustrating an exemplary patient-specific implant that can be used with and / or generated in accordance with the methods described herein according to embodiments. [Figure 12B] FIG. 11 is a diagram illustrating an exemplary patient-specific implant that can be used with and / or generated in accordance with the methods described herein according to embodiments. [Figure 13] This figure shows a segment of the patient's spine after several patient-specific implants have been placed there. [Modes for carrying out the invention]

[0007] The technology of the present invention relates to systems and methods for planning and implementing medical procedures and / or medical devices. For example, in many of the embodiments disclosed herein, a method for providing medical care includes the step of comparing a patient dataset of a patient to be treated with a set of reference patient datasets (e.g., data from previously treated patients). The method may include the step of selecting a subset of the reference patient dataset based, for example, on the similarity of the reference patient dataset to the patient dataset and / or whether the reference patient had a favorable treatment outcome. Using the selected subset, surgical procedures and / or medical device designs that are likely to achieve a favorable treatment outcome for such a particular patient can be generated. In some embodiments, the selected subset is analyzed to identify correlations between patient conditions, surgical procedures, device designs, and / or treatment outcomes, and these correlations are used to determine a personalized treatment protocol with a higher probability of success.

[0008] In the context of orthopedic surgery, systems with improved computer capabilities (e.g., predictive analytics, machine learning, neural networks, artificial intelligence (AI)) can use large datasets to determine improved or optimal surgical interventions and / or implant designs for specific patients. The patient's entire data can be characterized and compared with aggregated data from past patient populations (e.g., parameters, metrics, disease status, treatment, outcomes). In some embodiments, the systems described herein use this aggregated data to devise promising treatment options (e.g., surgical plans and / or implant designs for spinal and orthopedic procedures) and analyze the relevant success probabilities. These systems can further compare promising treatment options to determine the optimal patient-specific option that is expected to maximize the likelihood of a successful outcome.

[0009] For example, if a patient presents with a spinal deformity that can be represented using data including lumbar lordosis, Cobb angle, coronal parameters (e.g., coronal balance, global coronal balance, coronal plane pelvic tilt, etc.), sagittal parameters (e.g., pelvic incidence angle, sacral tilt, thoracic kyphosis angle, etc.), and / or pelvic parameters, an algorithm using these data points as inputs can be used to represent the optimal surgical plan and / or implant design for correcting the patient's condition and / or improving the patient's outcome. When additional data inputs (e.g., intervertebral disc height, segmental flexibility, bone quality, rotational displacement) are used to represent the condition, the algorithm can use these additional inputs to more precisely determine the optimal surgical plan and / or implant design for such a specific patient and their condition.

[0010] In some embodiments, the technology of the present invention can automatically or at least semi-automatically determine a corrective anatomical configuration for a patient suffering from one or more deformities. For example, the computer system described herein can identify similar patients by applying mathematical rules to selected parameters (e.g., lumbar lordosis, Cobb angle, etc.) and / or by analyzing a reference patient dataset, and based on these rules and / or comparisons with other patients, can provide a recommended anatomical configuration that represents the optimal outcome if the patient undergoes surgery. In some embodiments, the systems and methods described herein generate a virtual model of the corrective / recommended anatomical configuration (e.g., for surgical review).

[0011] In some embodiments, the technology of the present invention can automatically or at least semi-automatically generate a surgical plan to achieve the corrective anatomical configuration for the patient described above. For example, based on a virtual model of the corrective anatomical configuration, the systems and methods herein can determine the type of surgery (e.g., spinal fusion, non-fusion, etc.), the surgical technique (e.g., anterior, posterior, etc.), and / or spinal parameters for the corrective anatomical configuration (e.g., lumbar lordosis, Cobb angle, etc.). The surgical plan can be sent to the surgeon for review and approval. In some embodiments, the technology of the present invention can design one or more patient-specific implants to achieve the corrective anatomical configuration by the surgical plan.

[0012] In some embodiments, the technology of the present invention provides a system and method for generating multiple anatomical models of a patient. For example, a first model may represent the patient's innate (e.g., preoperative) anatomical configuration, and a second model may enable the simulation of the patient's corrected (e.g., postoperative) anatomical configuration. The second virtual model may optionally include one or more virtual implants, shown as being implanted in one or more target regions of the patient. Spinal metrics (e.g., lumbar lordosis, Cobb angle, coronal parameters, sagittal parameters, pelvic parameters, etc.) can be provided for both the preoperative and expected postoperative anatomical configurations.

[0013] In some embodiments, the technology of the present invention includes the step of generating, designing, and / or providing patient-specific medical procedures for multiple locations within a patient's body. For example, the technology of the present invention may include the step of identifying at least two target regions or target sites (e.g., a first vertebral level and a second vertebral level) within a patient's body for surgical intervention. The technology of the present invention can then design at least two patient-specific implants for implantation into the at least two target regions. Each of the at least two patient-specific implants can be specifically designed to fit its respective target region and thus can have a different shape. In some embodiments, the corrective anatomical configuration of the patient is achieved only by implanting each of the at least two patient-specific implants. For example, in the context of spinal surgery, the technology of the present invention can provide a first patient-specific intervertebral device to be implanted between the L2 and L3 vertebrae, a second patient-specific intervertebral device to be implanted between the L3 and L4 vertebrae, and a third patient-specific intervertebral device to be implanted between the L4 and L5 vertebrae.

[0014] In some embodiments, the technology of the present invention can be used to predict, model, or simulate disease progression in the body of a particular patient to assist in diagnosis and / or treatment planning. Simulations can be performed to model and / or estimate the patient's future anatomical configuration and / or spinal metrics in the event that no surgical intervention occurs, or (b) a variety of different surgical intervention options. Thus, progression modeling can be used to determine the optimal timing for surgical intervention and / or to select which surgical intervention will produce the best long-term outcome. In some embodiments, disease progression modeling is performed using one or more machine learning models trained on multiple reference patients.

[0015] In certain non-limiting cases, the technology of the present invention includes a method for providing patient-specific medical care to a patient. The method may include the step of receiving a patient dataset, which includes one or more images of the patient's spinal region showing the patient's innate anatomical configuration. Furthermore, the method may include the step of determining a corrective anatomical configuration for the patient that differs from the innate anatomical configuration, and the step of generating a virtual model of the corrective anatomical configuration. Furthermore, the method may include the step of generating a surgical plan, and the step of designing one or more patient-specific implants to achieve the corrective anatomical configuration in the patient. In a typical embodiment, the method described above may be carried out by a system that stores computer-executable instructions that cause the system to perform the steps of the method when executed.

[0016] In certain non-limiting cases, the technology of the present invention includes a method for designing a patient-specific orthopedic implant for a patient receiving treatment. The method may include a step of receiving a patient dataset of the patient, which includes spinal pathology data relating to the patient. The patient dataset may be compared with a plurality of reference patient datasets to identify one or more similar patient datasets within the plurality of reference patient datasets, each corresponding to a reference patient who has a similar spinal condition to the patient and has been treated with an orthopedic implant. Furthermore, the method may include a step of selecting one or more subsets of similar patient datasets based on whether the similar patient datasets indicated that the reference patients had a favorable outcome following the implantation of their orthopedic implants. Furthermore, the method may include a step of identifying surgical procedure data and designs for each orthopedic implant that resulted in a favorable outcome for at least one similar reference patient in the selected subset. Based on the design data and surgical procedure data that resulted in a favorable outcome for the similar reference patient, a patient-specific orthopedic implant for the patient and a surgical procedure for implanting it in the patient can be designed. In some embodiments, the method may further include a step of outputting a manufacturing command to cause a manufacturing system to produce a patient-specific orthopedic implant according to the generated design. In a typical embodiment, the method described above can be carried out by a system that stores computer-executable instructions that cause the system to perform the steps of the method when executed.

[0017] In the following, embodiments of the disclosed invention will be described more fully with reference to the accompanying drawings illustrating exemplary embodiments, where similar numbers represent similar elements through several figures. However, embodiments of the claims can be implemented in many different forms and should not be construed as being limited to the embodiments shown herein. The examples shown herein are non-limiting and are merely specific examples of several possible embodiments.

[0018] The words “to have,” “to possess,” “to contain,” and “to include,” and other forms thereof, are intended to be equivalent in meaning and to be non-restrictive in that the one or more items preceding any one of these words are not meant to be an exhaustive list of such one or more items, or to be limited to only the one or more items listed.

[0019] As used herein and in the claims, the singular forms "a," "an," and "the" include plural nouns unless the context clearly indicates otherwise.

[0020] While this disclosure primarily describes systems and methods for treatment planning in the context of orthopedic surgery, the technology of the present invention can be applied to treatments and devices in other fields (e.g., other types of surgical practice). Furthermore, while many embodiments herein represent systems and methods relating to implantable devices, the technology of the present invention can be equally applied to other types of medical devices (e.g., non-implantable devices).

[0021] Figure 1 is a network diagram showing a computer system 100 for providing patient-specific medical care according to an embodiment. As will be described in more detail herein, the system 100 is configured to generate a treatment plan for a patient. In some embodiments, the system 100 is configured to generate a treatment plan for a patient suffering from an orthopedic or spinal disease or disorder such as trauma (e.g., fracture), cancer, deformity, degeneration, pain (e.g., back pain, leg pain), abnormal spinal curvature (e.g., scoliosis, lordosis, kyphosis), abnormal spinal displacement (e.g., spondylolisthesis, lateral displacement, axial displacement), osteoarthritis, lumbar degenerative disc disease, cervical degenerative disc disease, lumbar spinal stenosis, or cervical spinal stenosis, or a combination thereof. The treatment plan may include surgical information, surgical plans, technical recommendations (e.g., device and / or instrument recommendations), and / or medical device designs. For example, a treatment plan may include at least one treatment procedure (e.g., a surgical procedure or surgical intervention) and / or at least one medical device (e.g., an implantable medical device (also referred to herein as "implant" or "implantable device") or an implant delivery device).

[0022] In some embodiments, System 100 generates a treatment plan, also referred to herein as a “patient-specific” or “personalized” treatment plan, which is personalized for a particular patient or group of patients. A patient-specific treatment plan may include at least one patient-specific surgical procedure and / or at least one patient-specific medical device that is designed and / or optimized to the patient’s specific characteristics (e.g., medical condition, biostructure, pathology, state, treatment history). For example, a patient-specific medical device may be specially designed and manufactured for a particular patient rather than being a ready-made device. However, it should be acknowledged that a patient-specific treatment plan may include aspects that are not personalized for a particular patient. For example, a patient-specific or personalized surgical procedure may include one or more instructions, parts, stages, etc., which are non-patient-specific. Similarly, a patient-specific or personalized medical device may include one or more components that are non-patient-specific and / or components that can be used together with instruments or tools that are non-patient-specific. Personalized implant designs can be used to manufacture or select patient-specific technologies, including medical devices, instruments, and / or surgical kits. For example, a personalized surgical kit may include one or more patient-specific devices, patient-specific instruments, non-patient-specific techniques (e.g., standard instruments, standard devices), instructions for use, patient-specific treatment plan information, or a combination thereof.

[0023] System 100 includes a client computer device 102, which can be a user device such as a smartphone, mobile device, laptop, desktop, personal computer, tablet, phablet, or other such device known in the art. As will be discussed in more detail herein, the client computer device 102 may include one or more processors and memory for storing instructions that can be executed by one or more processors to carry out the methods described herein. The client computer device 102 may be associated with a healthcare provider treating a patient. Figure 1 shows a single client computer device 102, but in alternative embodiments, it may be implemented as a client computer system encompassing multiple computer devices instead of one, and for that purpose the operations described herein with respect to the client computer device 102 may be carried out by this computer system and / or multiple computer devices instead.

[0024] The client computer device 102 is configured to receive a patient dataset 108 relating to the patient being treated. The patient dataset 108 may include data representing the patient's medical condition, biostructure, pathology, treatment history, preferences, and / or any other information or parameters relating to the patient. For example, patient dataset 108 may include treatment history, surgical intervention data, treatment outcome data, follow-up data (e.g., physician's diagnosis), patient feedback (e.g., quality of life questionnaires, feedback obtained using surveys), clinical data, healthcare provider information (e.g., physician, hospital, surgical team), patient information (e.g., demographic segment, sex, age, height, weight, disease type, occupation, activity level, tissue information, health assessment, comorbidities, health-related quality of life (HRQL)), life response, diagnostic results, medication information, allergies, imaging data (e.g., camera images, magnetic resonance imaging (MRI) images, ultrasound images, computed tomography (CAT) scan images, positron emission tomography (PET) images, X-ray images), or diagnostic equipment information (e.g., manufacturer, model number, specifications, user-selected settings / configuration, etc.). In some embodiments, the patient dataset 108 includes data representing one or more of the following: patient identification number (ID), age, sex, body mass index (BMI), lumbar lordosis, Cobb angle, pelvic angle of incidence, intervertebral disc height, segmental flexibility, bone quality, rotational displacement, and / or spinal treatment level.

[0025] The client computer device 102 is operably connected to the server 106 through the communication network 104, thereby enabling data transfer between the client computer device 102 and the server 106. The communication network 104 can be a wired network and / or a wireless network. If the communication network 104 is wireless, it can be implemented using communication technologies such as visible light communication (VLC), global interoperability for microwave access (WiMAX), long-term evolution (LTE), wireless local area network (WLAN), infrared (IR) communication, public switched telephone network (PSTN), radio waves, and / or other communication technologies known in the art.

[0026] Server 106, which may also be referred to as a “treatment support network” or “prescription analysis network,” may include one or more computer devices and / or computer systems. As will be discussed in more detail herein, Server 106 may include one or more processors and memory for storing instructions executable by one or more processors to carry out the methods described herein. In some embodiments, Server 106 is implemented as a distributed “cloud” computing system or device across any suitable combination of hardware and / or virtual computing resources.

[0027] The client computer device 102 and the server 106 can individually or collaboratively perform the various methods described herein to provide patient-specific medical care. For example, some or all of the steps of the methods described herein can be performed by the client computer device 102 alone, the server 106 alone, or a combination of the client computer device 102 and the server 106. Therefore, while certain operations are described herein in relation to the server 106, it should be acknowledged that these operations can also be performed by the client computer device 102, and vice versa.

[0028] Server 106 includes at least one database 110 configured to store reference data favorable to the treatment planning methods described herein. Reference data may include historical and / or clinical data from the same or other patients, data collected from past surgeries and / or other treatments of patients by the same or other healthcare providers, data relating to medical device design, data collected from research or study groups, data from field practice databases, data from academic institutions, data from implant or other medical device manufacturers, data from imaging studies, simulations, data from clinical trials, demographic data, treatment data, outcome data, or mortality data.

[0029] In some embodiments, database 110 includes multiple reference patient datasets, each relating to a corresponding reference patient. For example, a reference patient may be a patient who has previously received treatment or is currently receiving treatment. Each reference patient dataset may include data representing any other information or parameters about the reference patient, such as the patient's condition, biostructure, pathology, treatment history, disease progression, preferences, and / or any of the data described herein with respect to patient dataset 108. In some embodiments, a reference patient dataset may include preoperative data, intraoperative data, and / or postoperative data. For example, a reference patient dataset may include data representing one or more of the following: patient ID, age, sex, BMI, lumbar lordosis, Cobb angle, pelvic angle of incidence, intervertebral disc height, segmental flexibility, bone quality, rotational displacement, and / or spinal treatment level. As another example, a reference patient dataset may include treatment data relating to at least one treatment procedure performed on the reference patient, such as a description of the surgical procedure or surgical intervention (e.g., surgical technique, osteotomy, surgical procedure, orthodontic operation, implant or other device placement). In some embodiments, treatment data may include medical device design data relating to at least one medical device used to treat a reference patient, e.g., physical properties (e.g., size, shape, volume, material, mass, weight), mechanical properties (e.g., stiffness, strength, modulus of elasticity, hardness), and / or bio-properties (e.g., osseointegration, cell adhesion, antibacterial properties, antiviral properties). In yet another example, the reference patient dataset may include outcome data representing the treatment outcomes of the reference patient, e.g., corrective anatomical metrics, presence of fusion, HRQL, activity level, return to work, complications, recovery time, effectiveness, mortality, and / or reoperation.

[0030] In some embodiments, Server 106 receives at least a portion of reference patient datasets from multiple healthcare provider computer systems (e.g., systems 112a-112c, collectively 112). Server 106 can connect to the healthcare provider computer systems 112 through one or more communication networks (not shown). Each healthcare provider computer system 112 can be associated with a corresponding healthcare provider (e.g., a physician, surgeon, clinic, hospital, healthcare network, etc.). Each healthcare provider computer system 112 may contain at least one reference patient dataset (e.g., reference patient datasets 114a-114c, collectively 114) relating to a reference patient receiving treatment from the corresponding healthcare provider. The reference patient dataset 114 may include, for example, electronic medical records, electronic health records, biomedical datasets, etc. The reference patient dataset 114 can be received by Server 106 from the healthcare provider computer systems 112 and can be reformatted into various formats for storage in the database 110. Optionally, the reference patient dataset 114 may be processed (e.g., purified) to ensure that the represented patient parameters are likely to be favorable in the treatment planning described herein.

[0031] As will be described in more detail herein, the server 106 may be configured using one or more algorithms that generate patient-specific treatment plan data (e.g., treatment procedures, medical devices) based on reference data. In some embodiments, patient-specific data is generated based on the correlation between patient dataset 108 and reference data. Optionally, the server 106 may predict outcomes including recovery time, clinical endpoint-based effectiveness, probability of success, expected mortality, or expected reoperation. In some embodiments, the server 106 may continuously or periodically analyze patient data (including patient data obtained during patient hospitalization) to determine near real-time or real-time risk scores, mortality predictions, etc.

[0032] In some embodiments, the server 106 includes one or more modules for performing one or more stages of the patient-specific treatment planning method described herein. For example, in the embodiment described, the server 106 includes a data analysis module 116 and a treatment planning module 118. In alternative embodiments, one or more of these modules may be combined with or excluded from each other. Thus, while certain operations are described herein in relation to a particular set of modules, this description is not intended to be limiting, and such operations may be performed by different sets of modules in alternative embodiments.

[0033] The data analysis module 116 is comprised of one or more algorithms for identifying a subset of reference data from the database 110 that is likely to be advantageous in developing a patient-specific treatment plan. For example, the data analysis module 116 can identify similar data (e.g., one or more similar patient datasets within the reference patient dataset) by comparing patient-specific data (e.g., patient dataset 108 received from a client computer device 102) with reference data from the database 110 (e.g., a reference patient dataset). This comparison can be based on one or more parameters such as age, sex, BMI, lumbar lordosis, pelvic angle of incidence, and / or treatment level. A similarity score can be calculated for each reference patient using these parameters. The similarity score can represent the statistical correlation between the patient dataset 108 and the reference patient dataset. Thus, similar patients can be identified based on whether the similarity score is greater than, below, or at a specified threshold. For example, as will be described in more detail below, the above comparison can be performed by assigning values ​​to each parameter to determine the aggregate difference between the treated patient and each reference patient. Reference patients with aggregate differences smaller than the threshold can be considered similar patients.

[0034] The data analysis module 116 may be further configured using one or more algorithms to select a subset of reference patient datasets based on similarity to the patient dataset 108 and / or the treatment outcomes of corresponding reference patients. For example, the data analysis module 116 may identify one or more similar patient datasets within the reference patient dataset and then select a subset of similar patient datasets based on whether or not these similar patient datasets contain data indicating a favorable or desirable treatment outcome. Outcome data may include data representing one or more outcome parameters such as corrective anatomical metrics, presence of fusion, HRQL, activity level, complications, recovery time, efficacy, mortality, or reoperation. In some embodiments, as will be described in more detail below, the data analysis module 116 calculates an outcome score by assigning a value to each outcome parameter. If the outcome score is greater than, below, or at a specified threshold, the patient may be considered to have a favorable outcome.

[0035] In some embodiments, the data analysis module 116 selects a subset of reference patient datasets based at least in part on user input (e.g., from clinicians, surgeons, physicians, or healthcare providers). For example, user input can be used to identify similar patient datasets. In some embodiments, similarity parameters and / or outcome parameters can be selected by the healthcare provider to adjust similarity scores and / or outcome scores based on clinician input. In yet another embodiment, the healthcare provider or physician can select (or define new similarity parameters and / or outcome parameters) to be used to generate similarity scores and / or outcome scores, respectively.

[0036] In some embodiments, the data analysis module 116 includes one or more algorithms used to select a set or subset of reference patient datasets based on criteria other than patient parameters. For example, these one or more algorithms can be used to select a subset based on healthcare provider parameters (e.g., based on healthcare provider ratings / scores such as hospital / physician expertise, number of procedures performed, hospital ratings), and / or healthcare resource parameters (e.g., diagnostic equipment, surgical equipment such as surgical robots), or other non-patient-related information that can be used to predict outcomes and risk profiles for procedures relating to the current healthcare provider. For example, reference patient datasets with images taken from similar diagnostic equipment can be aggregated to reduce or limit irregularities caused by changes between diagnostic equipment. Furthermore, data from similar healthcare providers (e.g., healthcare providers with conventionally similar outcomes, physician expertise, surgical teams, etc.) can be used to develop patient-specific treatment plans for a particular healthcare provider. In some embodiments, reference healthcare provider datasets, hospital datasets, physician datasets, surgical team datasets, post-treatment datasets, and other datasets can be utilized. For example, a patient-specific treatment plan for performing field surgery can be based on baseline patient data from similar field surgery and / or related datasets. In another example, a patient-specific treatment plan can be generated based on the available robotic surgical system. The baseline patient dataset can be selected based on patients who have undergone surgery using a comparable robotic surgical system under similar conditions (e.g., size and capabilities such as surgical team and hospital resources).

[0037] The treatment planning module 118 is configured with one or more algorithms that generate at least one treatment plan (e.g., a preoperative plan, a surgical plan, a postoperative plan, etc.) based on the output of the data analysis module 116. In some embodiments, the treatment planning module 118 is configured to develop and / or implement at least one predictive model, also known as a “prescription model,” for generating patient-specific treatment plans. The predictive model can be developed using clinical knowledge, statistics, machine learning, AI, or neural networks, etc. In some embodiments, the output from the data analysis module 116 is analyzed (e.g., using statistics, machine learning, neural networks, or AI) to identify correlations between datasets, patient parameters, healthcare provider parameters, healthcare resource parameters, treatment procedures, medical device designs, and / or treatment outcomes. Using these correlations, at least one predictive model can be developed that predicts the likelihood that a treatment plan will result in a favorable outcome for a particular patient. The predictive model can be validated, for example, by inputting data into it and comparing the model’s output with the predictive output.

[0038] In some embodiments, the treatment planning module 118 is configured to generate a treatment plan based on previous treatment data from a reference patient. For example, the treatment planning module 118 can receive a selected subset of a reference patient dataset and / or similar patient dataset from the data analysis module 116 and identify treatment data from this subset. The treatment data may include, for example, treatment procedure data (e.g., surgical procedure data or surgical intervention data) and / or medical device design data (e.g., implant design data) relating to preferred or desirable treatment outcomes for the corresponding patient. The treatment planning module 118 can analyze the treatment procedure data and / or medical device design data to determine the optimal treatment protocol for the patient being treated. For example, values ​​can be assigned to the treatment procedures and / or medical device designs and aggregated to generate a treatment score. A patient-specific treatment plan can be determined by selecting a treatment plan based on this score (e.g., a high or best score, a low or lowest score, a score greater than or below a specified threshold, or a score at or within this threshold). A personalized patient-specific treatment plan may be at least partially based on patient-specific technology or patient-specific technology of choice.

[0039] Alternatively, or in combination with the above, the treatment planning module 118 can generate treatment plans based on correlations between datasets. For example, the treatment planning module 118 can correlate treatment procedure data and / or medical device design data (e.g., identified by the data analysis module 116) from similar patients with favorable outcomes. Correlation analysis may include a step of converting correlation coefficient values ​​into values ​​or scores. The values / scores can be aggregated, filtered, or otherwise analyzed to determine a statistical significance of 1 or more. These correlations can be used to determine treatment procedures and / or medical device designs that are optimal or produce favorable outcomes for the patient being treated.

[0040] Alternatively, or in combination therewith, the treatment planning module 118 may generate treatment plans using one or more AI technologies. AI technologies can be used to develop computer systems that simulate human intelligence, such as learning, reasoning, planning, problem-solving, and decision-making. AI technologies may include, but are not limited to, case-based reasoning, rule-based systems, artificial neural networks, decision trees, support vector machines, regression analysis, Bayesian networks (e.g., naive Bayesian classifiers), genetic algorithms, cellular automata, fuzzy logic systems, multi-agent systems, swarm intelligence, data mining, machine learning (e.g., supervised learning, unsupervised learning, reinforcement learning), and hybrid systems.

[0041] In some embodiments, the treatment planning module 118 generates a treatment plan using one or more trained machine learning models. Various types of machine learning models, algorithms, and techniques are suitable for use in combination with the techniques of the present invention. In some embodiments, the machine learning model is first trained on a training dataset, which is a set of examples for fitting the model's parameters (e.g., the weights of the connections between "neurons" in an artificial neural network). For example, the training dataset may include any of the reference data stored in the database 110, such as multiple reference patient datasets or a selected subset thereof (e.g., multiple similar patient datasets).

[0042] In some embodiments, a machine learning model (e.g., a neural network or a Naive Bayesian classifier) ​​can be trained on a training dataset using a supervised learning method (e.g., gradient descent or stochastic gradient descent). The training dataset can include pairs of occurrence "input vectors" and their corresponding associated "response vectors" (generally represented as targets). This model is run on the training dataset to produce results, which are then compared to the targets for each input vector in the training dataset. Based on the results of this comparison and the specific learning algorithm used, the model parameters are adjusted. Model fitting can include both variable selection and parameter estimation. The fitted model can be used to predict the response to observations in a second dataset called a validation dataset. The validation dataset can provide an unbiased evaluation of the model fit on the training dataset while adjusting the model parameters. The validation dataset can be used for regularization by early stopping, for example, by stopping training when an increase in errors on the validation dataset may indicate an overfit to the training dataset. In some embodiments, the validation dataset error can change during training, and therefore, temporary rules can be used to determine when overfitting has definitely begun. Finally, the test dataset can be used to provide an unbiased evaluation of the final model fit to the training dataset.

[0043] To generate a treatment plan, a patient dataset 108 can be input into a trained machine learning model. Additional data, such as a reference patient dataset and / or a selected subset of similar patient datasets, and / or treatment data from this selected subset, can be input into the trained machine learning model. The trained machine learning model can then calculate whether various candidate treatment procedures and / or medical device designs are likely to produce a favorable outcome for the patient. Based on these calculations, the trained machine learning model can select at least one treatment plan for the patient. In embodiments where multiple trained machine learning models are used, these models can be run sequentially or simultaneously to compare outcomes and can be periodically updated using the training dataset. The treatment plan module 118 can use one or more of the machine learning models based on their predicted accuracy scores.

[0044] A patient-specific treatment plan generated by the treatment planning module 118 may include at least one patient-specific treatment procedure (e.g., a surgical procedure or surgical intervention) and / or at least one patient-specific medical device (e.g., an implant or implant delivery device). The patient-specific treatment plan may include the entirety or a portion thereof of a surgical procedure. Furthermore, one or more patient-specific medical devices may be specially selected or designed to match the corresponding surgical procedure, thereby enabling the use of a combination of various components of patient-specific technology to treat the patient.

[0045] In some embodiments, patient-specific treatment procedures include orthopedic surgical procedures such as spinal surgery, hip surgery, knee surgery, jaw surgery, hand surgery, shoulder surgery, elbow surgery, total joint reconstruction (arthroplasty), skull reconstruction, foot surgery, or ankle surgery. Spinal surgery may include spinal fusion procedures such as posterior lumbar interbody fusion (PLIF), anterior lumbar interbody fusion (ALIF), transverse lumbar interbody fusion or transforaminal lumbar interbody fusion (TLIF), lateral lumbar interbody fusion (LLIF), direct transverse lumbar interbody fusion (DLIF), and transverse lumbar interbody fusion (XLIF). In some embodiments, patient-specific treatment procedures include descriptions and / or instructions for performing one or more of their embodiments. For example, patient-specific surgical procedures may include one or more of surgical techniques, corrective operations, osteotomies, or implant placements.

[0046] In some embodiments, patient-specific medical device design includes design for orthopedic implants and / or design for instruments for delivering such implants. Examples of such implants include, but are not limited to, screws (e.g., bone screws, spinal screws, vertebral arc root screws, facet screws), intervertebral implantation devices (e.g., intervertebral implants), cages, plates, rods, discs, fixation devices, spacers, rods, expandable devices, stents, brackets, cords, scaffolds, anchoring devices, anchors, nuts, bolts, rivets, connectors, tethers, fasteners, joint replacements, or hip implants. Examples of instruments include, but are not limited to, screw guides, cannulas, ports, catheters, or insertion tools.

[0047] A patient-specific medical device design may include data representing one or more of the following physical properties of the corresponding medical device: (e.g., size, shape, volume, material, mass, weight), mechanical properties (e.g., stiffness, strength, modulus of elasticity, hardness), and / or biomimetic properties (e.g., osseointegration, cell adhesion, antibacterial properties, antiviral properties). For example, a design for an orthopedic implant may include the shape, size, material, and / or effective stiffness of the implant (e.g., lattice density, number of struts, strut placement, etc.). In some embodiments, the resulting patient-specific medical device design is a design for the entire device. Alternatively, the resulting design may be for one or more components of the device rather than the entire device.

[0048] In some embodiments, the design is for one or more patient-specific device components that can be used in conjunction with standard off-the-shelf components. For example, a spinal arc root screw kit in spinal surgery may include both standard components and individual patient-specific components. In some embodiments, the resulting design is for a patient-specific medical device that can be used in conjunction with standard off-the-shelf delivery instruments. For example, the implant (e.g., screw, screw holder, rod) may be designed and manufactured to suit the patient, while the instrument for delivering the implant may be a standard instrument. This approach allows the implanted components to be designed and manufactured based on the surgeon's preference for improving the patient's biostructure and / or treatment. The patient-specific devices described herein are expected to improve delivery into the patient's body, placement at the treatment site, and / or interaction with the patient's biostructure.

[0049] In embodiments where a patient-specific treatment plan includes a surgical procedure for implanting a medical device, the treatment plan module 118 can store various types of implant surgery information, such as implant parameters (e.g., type, dimensions), implant availability, preoperative planning aspects (e.g., initial implant configuration, detection and measurement of the patient's biostructure), or FDA requirements for the implant (e.g., specific implant parameters and / or implant characteristics related to compliance with FDA regulations). In some embodiments, the treatment plan module 118 can convert the implant surgery information into a format usable by machine learning-based models and algorithms. For example, the implant surgery information can be tagged with a specific identifier by type, or converted into a numerical representation suitable for feeding into a trained machine learning model. The treatment plan module 118 can store information about the patient's biostructure, such as two-dimensional or three-dimensional images or models of the biostructure, and / or information about the bio, morphological, and / or mechanical properties of the biostructure. The biostructure information can be used to inform the design and / or placement of the implant.

[0050] The treatment plan generated by the treatment planning module 118 can be transmitted to a client computer device 102 via a communication network 104 for output to a user (e.g., a clinician, surgeon, healthcare provider, or patient). In some embodiments, the client computer device 102 includes or is operably coupled with a display 122 for outputting the treatment plan. The display 122 may include a graphical user interface (GUI) for visually representing various aspects of the treatment plan. For example, the display 122 may show various aspects of the surgical procedure performed on the patient, such as surgical technique, treatment level, orthodontic operation, tissue resection, and / or implant placement. To facilitate visualization, a virtual model of the surgical procedure may be displayed. As another example, the display 122 may show a design for a medical device to be implanted in the patient, such as a two-dimensional or three-dimensional model of the device design. The display 122 may show patient information, such as a two-dimensional or three-dimensional image or model of the patient's biostructure on which the surgical procedure is performed and / or the device is to be implanted. The client computer device 102 may further include one or more user input devices (not shown) that enable the user to modify, select, approve, and / or reject the displayed treatment plan.

[0051] In some embodiments, the medical device design generated by the treatment planning module 118 can be transmitted from the client computer device 102 and / or server 106 to a manufacturing system 124 for manufacturing the corresponding medical device. The manufacturing system 124 can be located on-site or off-site. On-site manufacturing can reduce the number of patient visits and / or shorten the time available for performing surgery, while off-site manufacturing can be advantageous for manufacturing complex devices. Off-site manufacturing facilities may have specialized manufacturing equipment. In some embodiments, more complex device components can be manufactured off-site, while only simpler device components can be manufactured on-site.

[0052] Various types of manufacturing systems are suitable for use according to the embodiments herein. For example, manufacturing system 124 can be configured for additive manufacturing such as three-dimensional (3D) printing, stereolithography (SLA), digital photolithography (DLP), fused deposition modeling (FDM), selective laser sintering (SLS), selective laser melting (SLM), selective heat sintering (SHM), electron beam melting (EBM), laminated material manufacturing (LOM), powder bed printing (PP), thermoplastic printing, direct material deposition (DMD), inkjet photopolymer printing, or similar techniques, or combinations thereof. Alternatively or in combination therewith, manufacturing system 124 can be configured for subtractive (conventional) manufacturing such as CNC fabrication, electrical discharge manufacturing (EDM), grinding, laser cutting, waterjet machining, manual machining (e.g., milling, turning), or similar techniques, or combinations thereof. The manufacturing system 124 can manufacture one or more patient-specific medical devices based on manufacturing instructions or manufacturing data (e.g., CAD data, 3D data, digital blueprints, stereolithography data, or data suitable for the various manufacturing techniques described herein). Various components of system 100 can generate at least a portion of the manufacturing data used by the manufacturing system 124. The manufacturing data includes, but is not limited to, manufacturing instructions (e.g., programs executable by additive manufacturing equipment, subtractive manufacturing equipment, etc.), 3D data, CAD data (e.g., CAD files), CAM data (e.g., CAM files), path data (e.g., print head paths, tool paths, etc.), material data, tolerance data, or surface finish data (e.g., surface roughness data), regulatory data (e.g., FDA requirements, compensation data, etc.), etc. The manufacturing system 124 can analyze the manufacturability of an implant design based on the received manufacturing data. An implant design can be established by modifying the shape, surfaces, etc., and then generating a manufacturing instruction. In some embodiments, the server 106 generates at least a portion of the manufacturing data that is sent to the manufacturing system 124.

[0053] The manufacturing system 124 can generate CAM data, printing data (e.g., powder bed printing data, thermoplastic printing data, or photopolymer data), and may include additive manufacturing equipment, subtractive manufacturing equipment, or heat treatment equipment. Additive manufacturing equipment may include 3D printers, stereolithography devices, digital photoprocessing devices, melt deposition modeling devices, selective laser sintering devices, selective laser melting devices, electron beam melting devices, laminate manufacturing devices, powder bed printers, thermoplastic material printers, direct material deposition devices, or inkjet photopolymer printers, or similar technologies. Subtractive manufacturing equipment may include CNC machines, electrical discharge machines, grinders, laser cutting machines, water jet machines, manual manufacturing machines (e.g., milling machines, lathes, etc.), or similar technologies. Using both additive and subtractive technologies, implants with complex shapes, surface finishes, materials, etc., can be manufactured. The generated manufacturing instructions can be configured to cause the manufacturing system 124 to manufacture a patient-specific orthopedic implant that conforms to or is therapeutically effective to a patient-specific design. In some embodiments, patient-specific medical devices may include features, materials, and designs that are shared across multiple designs to simplify manufacturing. For example, implantable patient-specific medical devices for various patients may have similar internal implantation mechanisms but different implantation configurations. In some embodiments, components of a patient-specific medical device are selected from a set of available prefabricated components, and the selected prefabricated components may be modified based on manufacturing orders or manufacturing data.

[0054] The treatment plans described herein can be performed by a surgeon, a surgical robot, or a combination thereof, thereby providing treatment flexibility. In some embodiments, the surgical procedure can be performed entirely by a surgeon, entirely by a surgical robot, or a combination thereof. For example, one stage of the surgical procedure can be performed manually by a surgeon, and another stage of this procedure can be performed by a surgical robot. In some embodiments, the treatment planning module 118 generates control commands configured to cause a surgical robot (e.g., a robotic surgical system, a navigation system, etc.) to perform the surgical procedure partially or entirely. The control commands can be transmitted by a client computer device 102 and / or a server 106 to the robotic device.

[0055] Following the treatment of a patient according to the treatment plan, the treatment progress can be monitored over one or more periods to update the data analysis module 116 and / or the treatment planning module 118. Post-treatment data can be added to the baseline data stored in the database 110. Using the post-treatment data, machine learning models can be trained to develop patient-specific treatment plans, patient-specific medical devices, or combinations thereof.

[0056] It should be acknowledged that the components of system 100 can be in many different forms. For example, in an alternative embodiment, the database 110, the data analysis module 116, and / or the treatment planning module 118 can be components of client computer device 102 rather than server 106. As another example, the database 110, the data analysis module 116, and / or the treatment planning module 118 can be located across multiple different servers, computer systems, or other types of cloud computing resources, rather than being located on a single server 106 or client computer device 102.

[0057] Furthermore, in some embodiments, System 100 can operate in many other computer system environments or configurations. Examples of computer systems, environments, and / or configurations that may be suitable for use in conjunction with the technology of the present invention include, but are not limited to, personal computers, server computers, handheld or laptop devices, cellular phones, wearable electronic devices, tablet devices, microprocessor systems, microprocessor-based systems, programmable garden appliances, network PCs, minicomputers, mainframe computers, distributed computer environments including any of these systems or devices, and the like.

[0058] Figure 2 shows a computer device 200 suitable for use with the system 100 of Figure 1 according to an embodiment. The computer device 200 can be incorporated into various components of the system 100 of Figure 1, such as a client computer device 102 or a server 106. The computer device 200 includes one or more processors 210 (e.g., CPU, GPU, HPU, etc.). The processor 210 can be a single processing unit or multiple processing units distributed across multiple devices, or within a single device. The processor 210 can be coupled to other hardware devices using a bus, such as a PCI bus or a SCSI bus. The processor 210 can be configured to execute one or more computer-readable program instructions, such as program instructions for performing any of the methods described herein.

[0059] The computer device 200 may include, for example, one or more input devices 220 that provide input to the processor 210 to notify the processor 210 of actions from the user of device 200. These actions can be mediated by a hardware controller that interprets signals received from the input devices and communicates the information to the processor 210 using a communication protocol. The input devices 220 may include, for example, a mouse, keyboard, touch screen, infrared sensor, touchpad, wearable input device, camera or image-based input device, microphone, or other user input device.

[0060] The computer device 200 may include a display 230 used to display various types of output, such as text, models, virtual procedures, surgical plans, implants, graphics, and / or images (e.g., images having voxels representing radiation density units or Hounsfield units representing the density of tissue at a given location). In some embodiments, the display 230 provides the user with graphic and textual visual feedback. The processor 210 can communicate with the display 230 through a hardware controller for the device. In some embodiments, the display 230 includes the input device 220 as part of the display 230 if the input device 220 includes a touch screen or if the input device 220 is equipped with an eye-direction monitoring system. In alternative embodiments, the display 230 is separate from the input device 220. Examples of display devices include LCD display screens, LED display screens, projection displays, holographic displays, or augmented reality displays (e.g., head-up display devices or head-mounted devices), and others.

[0061] Optionally, the processor 210 may be connected to other I / O devices 240 such as network cards, video cards, audio cards, USB, FireWire or other external devices, cameras, printers, speakers, CD-ROM drives, DVD drives, disk drives, or Blu-ray devices. Other I / O devices 240 may include input ports for information from directly connected medical devices, such as imaging devices including MRI machines, X-ray machines, and CT machines. Furthermore, other I / O devices 240 may include input ports for receiving data from these types of machines from other sources, via a network or from previously captured data stored, for example, in a database.

[0062] In some embodiments, the computer device 200 further includes a communication device (not shown) having the ability to communicate wirelessly or via a wired connection with a network node. The communication device can communicate with another device or server over a network using, for example, the TCP / IP protocol. The computer device 200 can distribute its operations across multiple network devices, including imaging equipment, manufacturing equipment, etc., using the communication device.

[0063] The computer device 200 may include memory 250, which may reside in a single device or be distributed across multiple devices. Memory 250 may include one or more hardware devices for volatile or non-volatile storage, and may include both read-only and writable memory. For example, memory may include random access memory (RAM), various caches, CPU registers, read-only memory (ROM), and writable non-volatile memory, such as flash memory, hard drives, floppy disks, CDs, DVDs, magnetic storage devices, tape drives, or device buffers. Memory is not a propagated signal separated from the underlying hardware and is therefore non-temporary. In some embodiments, memory 250 is a non-temporary computer-readable storage medium for storing, for example, programs, software, data, etc. In some embodiments, memory 250 may include program memory 260 for storing an operating system 262, one or more treatment support modules 264, and other application programs 266. The treatment support module 264 may include one or more modules (for example, the data analysis module 116 and / or treatment planning module 118 described with respect to Figure 1) configured to perform the various methods described herein. The memory 250 may also include a data memory 270 which may contain, for example, reference data, configuration data, settings, user options, or user preferences that can be supplied to the program memory 260 of the computer device 200 or any other element.

[0064] Figure 3 is a flowchart illustrating a method 300 for providing patient-specific medical care according to an embodiment. The method 300 may include a data phase 310, a modeling phase 320, and an execution phase 330. The data phase 310 may include steps of collecting data from the patient being treated (e.g., pathology data) and comparing the patient data to reference data (e.g., historical patient data such as pathology data, surgical data, and / or outcome data). For example, a patient dataset may be received (block 312). For example, a patient dataset may be compared to multiple reference patient datasets to identify one or more similar patient datasets within a plurality of reference patient datasets (block 314). Each of the plurality of reference patient datasets may include data representing one or more of the following: age, sex, BMI, lumbar lordosis, Cobb angle, pelvic incidence angle, intervertebral disc height, segmental flexibility, bone quality, rotational displacement, or spinal treatment level.

[0065] A subset of multiple reference patient datasets can be selected, for example, based on similarity to the patient dataset and / or the treatment outcomes of the corresponding reference patients (block 316). For example, a similarity score can be generated for each reference patient dataset based on a comparison between the patient dataset and the reference patient dataset. The similarity score can represent a statistical correlation between the patient data and the reference patient dataset. One or more similar patient datasets can be identified, at least partially, based on the similarity score.

[0066] In some embodiments, each patient dataset in a selected subset includes and / or is associated with a preferred treatment outcome (e.g., a single-target outcome, an aggregate outcome score, or a preferred treatment outcome based on an outcome threshold setting). These data may include, for example, data representing one or more of the following: corrective anatomical metrics, the presence of fusion, health-related quality of life, activity levels, or complications. In some embodiments, these data may be or include an outcome score that can be calculated based on a single-target outcome, an aggregate outcome, and / or an outcome threshold.

[0067] Optionally, data analysis phase 310 may include a step of identifying or determining surgical procedure data and / or medical device design data relating to preferred treatment outcomes for at least one patient dataset of a selected subset (e.g., for at least one similar patient dataset). Surgical procedure data may include data representing one or more of the following: surgical techniques, orthodontic operations, bone resections, or implant placements. At least one medical device design may include data representing one or more of the following: physical, mechanical, or biological properties of the corresponding medical device. In some embodiments, at least one patient-specific medical device design includes a design for an implant or implant delivery device.

[0068] In the modeling phase 320, surgical procedures and / or medical device designs are generated (block 322). This generation phase may include developing at least one predictive model based on a selected subset of patient datasets and / or reference patient datasets (e.g., using statistics, machine learning, neural networks, or AI). The predictive model may be configured to generate surgical procedures and / or medical device designs.

[0069] In some embodiments, the predictive model includes one or more trained machine learning models that generate surgical procedures and / or medical device designs at least partially. For example, the trained machine learning models can determine several candidate surgical procedures and / or medical device designs for treating the patient. Each surgical procedure can be associated with a corresponding medical device design. In some embodiments, the surgical procedures and / or medical device designs are determined based on surgical procedure data and / or medical device design data regarding a favorable outcome, as described above with respect to the data analysis phase 310. A machine learning model trained for each surgical procedure and / or corresponding medical device design can calculate the probability of producing a target outcome (e.g., a favorable or desirable outcome) for the patient. The trained machine learning models can then select at least one surgical procedure and / or corresponding medical device design based at least partially on the calculated probabilities.

[0070] Execution phase 330 may include a step (block 332) of manufacturing the medical device design. In some embodiments, the medical device design is manufactured by a manufacturing system configured to perform one or more of the following: additive manufacturing, 3D printing, stereolithography, digital photoprocessing, fusion deposition modeling, selective laser sintering, selective laser melting, electron beam melting, laminate manufacturing, powder bed printing, thermoplastic printing, direct material deposition, or inkjet photopolymer printing. Execution phase 330 may optionally include a step of generating a manufacturing order configured to cause the manufacturing system to manufacture a medical device having the medical device design.

[0071] The execution phase 330 may include a step (block 334) in which a surgical procedure is performed. The surgical procedure may include a step in which a medical device having the medical device design is implanted in the patient. The surgical procedure may be performed manually, by a surgical robot, or a combination thereof. In embodiments in which the surgical procedure is performed by a surgical robot, the execution phase 330 may include a step in which control commands are generated that are configured to cause the surgical robot to perform at least partially a patient-specific surgical procedure.

[0072] Method 300 can be implemented and executed in various ways. In some embodiments, one or more steps of Method 300 (e.g., data phase 310 and / or modeling phase 320) can be stored in memory and implemented as computer-readable instructions executable by one or more processors of any of the computer devices and computer systems described herein (e.g., system 100) or its components (e.g., client computer device 102 and / or server 106). Alternatively, one or more steps of Method 300 (e.g., execution phase 330) can be implemented by healthcare providers (e.g., physicians, surgeons), robotic devices (e.g., surgical robots), manufacturing systems (e.g., manufacturing system 124), or a combination thereof. In some embodiments, one or more steps of Method 300 are omitted (e.g., execution phase 330).

[0073] Figures 4A to 4C illustrate exemplary datasets that may be used and / or generated in conjunction with the methods described herein according to embodiments (e.g., data analysis phase 310 described with respect to Figure 3). Figure 4A shows a patient dataset 400 of patients being treated. The patient dataset 400 may include patient ID and several preoperative patient metrics (e.g., age, sex, BMI, lumbar lordosis (LL), pelvic incidence angle (PI), and spinal treatment level (level)). Figure 4B shows several reference patient datasets 410. In the embodiments described, the reference patient dataset 410 includes a first subset 412 from a study group (Study Group X), a second subset 414 from a clinical practice database (Clinical Practice Y), and a third subset 416 from an academic group (University Z). In alternative embodiments, the reference patient dataset 410 may include data from other sources as described herein. Each reference patient dataset may include a patient ID, multiple preoperative patient metrics (e.g., age, sex, BMI, lumbar lordosis (LL), pelvic incidence angle (PI), and spinal treatment level (level)), treatment outcome data (e.g., presence of fusion (fused), HRQL, complications), and treatment procedure data (surgical intervention) (e.g., implant design, implant placement, surgical technique).

[0074] Figure 4C shows a comparison of patient dataset 400 with reference patient dataset 410. As described above, patient dataset 400 can be compared with reference patient dataset 410 to identify one or more similar patient datasets from multiple reference patient datasets. In some embodiments, to calculate a similarity score 420 ("preoperative similarity") for each reference patient dataset, patient metrics from reference patient dataset 410 are converted to numerical values ​​and compared with patient metrics from patient dataset 400. Reference patient datasets with similarity scores below a threshold can be considered similar to patient dataset 400. For example, in the embodiment described, reference patient dataset 410a has a similarity score of 9, reference patient dataset 410b has a similarity score of 2, reference patient dataset 410c has a similarity score of 5, and reference patient dataset 410d has a similarity score of 8. Since each of these scores is below the threshold of 10, reference patient datasets 410a to 410d are identified as similar patient datasets.

[0075] By analyzing treatment outcome data from similar patient datasets 410a to 410d, the surgical procedure and / or implant design with the highest probability of success can be determined. For example, treatment outcome data for each reference patient dataset can be converted into a numerical outcome score 430 ("outcome rate") representing the likelihood of a favorable outcome. In the embodiment described, reference patient dataset 410a has an outcome score of 1, reference patient dataset 410b has an outcome score of 1, reference patient dataset 410c has an outcome score of 9, and reference patient dataset 410d has an outcome score of 2. In embodiments where a lower outcome score correlates to a higher likelihood of a favorable outcome, patient datasets 410a, 410b, and 410d can be selected. Then, using treatment procedure data from the selected reference patient datasets 410a, 410b, and 410d, at least one surgical procedure (e.g., implant placement, surgical technique) and / or implant design that is likely to produce a favorable outcome for the patient being treated can be determined.

[0076] In some embodiments, a method is provided for providing medical care to a patient. The method may include a step of comparing a patient dataset with reference data. The patient dataset and reference data may include any of the data types described herein. The method may include a step of identifying and / or selecting relevant reference data (e.g., data relating to the treatment of the patient, such as data on similar patients and / or data on similar treatment procedures) using any of the techniques described herein. Based on the selected data, a treatment plan may be generated using any of the techniques described herein. The treatment plan may include one or more treatment procedures (e.g., surgical procedures, instructions for procedures, models or other virtual representations of procedures), one or more medical devices (e.g., implantable devices, instruments for delivering devices, surgical kits), or a combination thereof.

[0077] In some embodiments, a system for generating a treatment plan is provided. The system can compare a patient dataset with a plurality of reference patient datasets using any of the techniques described herein. For example, a subset of the plurality of reference patient data can be selected based on similarity and / or treatment outcomes or any of the other techniques described herein. A treatment plan can be generated using any of the techniques described herein, at least partially based on the selected subset. The treatment plan may include one or more treatment procedures, one or more medical devices, any other aspect of the treatment plan described herein, or a combination thereof.

[0078] In yet another embodiment, the system is configured to use patient historical data. The system can select patient historical data to develop or select treatment plans or design medical devices, etc. It can select historical data based on one or more similarities between the current patient and past patients to develop a prescriptive treatment plan designed to meet a desired outcome. The prescriptive treatment plan can be tailored to the current patient to increase the likelihood of the desired outcome. In some embodiments, the system can analyze and / or select a subset of historical data to generate one or more treatment procedures, one or more medical devices, or a combination thereof. In some embodiments, the system can use a subset of data from one or more groups of past patients who had a favorable outcome to generate a baseline historical dataset that can be used, for example, to design, develop, or select treatment plans, medical devices, or a combination thereof.

[0079] Figure 5 is a flowchart illustrating a method 500 for providing patient-specific medical care according to another embodiment of the technology of the present invention. Method 500 can begin by receiving a patient dataset relating to a specific patient requiring treatment in step 502. The patient dataset may include data representing the patient's medical condition, biostructure, pathology, symptoms, treatment history, preferences, and / or any other information or parameters relating to the patient. For example, patient dataset 808 may include surgical intervention data, treatment outcome data, progress data (e.g., surgeon's report), patient feedback (e.g., quality of life questionnaire, feedback obtained using surveys), clinical data, patient information (e.g., demographic segment, sex, age, height, weight, type of medical condition, occupation, activity level, tissue information, health assessment, comorbidities, health-related quality of life (HRQL)), life response, diagnostic results, medication information, allergies, or diagnostic device information (e.g., manufacturer, model number, specifications, user selection settings / configuration, etc.). The patient dataset may include image data such as camera images, magnetic resonance imaging (MRI) images, ultrasound images, computed tomography (CAT) scan images, positron emission tomography (PET) images, or X-ray images. In some embodiments, the patient dataset may include data representing one or more of the following: patient identification number (ID), age, sex, body mass index (BMI), lumbar lordosis, Cobb angle, pelvic incidence angle, intervertebral disc height, segmental flexibility, bone quality, rotational displacement, and / or spinal treatment level. The patient dataset may be received by a server, computer device, or other computer system. For example, in some embodiments, the patient dataset may be received by a server 106 shown in Figure 1 or a computer system 606 described below with reference to Figure 6. In some embodiments, the computer system receiving the patient dataset in step 502 may also store one or more software modules (e.g., a data analysis module 116 and / or a treatment planning module 118 shown in Figure 1, or yet another software module for performing various operations of method 500). Further details regarding the collection and reception of patient datasets are explained below with reference to Figures 6-7D.

[0080] In some embodiments, the received patient dataset may include disease metrics such as lumbar lordosis, Cobb angle, coronal parameters (e.g., coronal balance, global coronal balance, coronal plane pelvic tilt, etc.), sagittal parameters (e.g., pelvic incidence angle, sacral tilt, thoracic kyphosis angle, etc.), and / or pelvic parameters. Disease metrics may include microscopic measurements (e.g., metrics relating to the identification or individual connections of the patient's spine) and / or macroscopic measurements (e.g., metrics relating to multiple connections of the patient's spine). In some embodiments, disease metrics may not be included in the patient dataset, and Method 500 may include a step of determining one or more of the disease metrics based on patient imaging data (e.g., automatically determining them), as described below.

[0081] With the patient dataset received in step 502, method 500 can continue in step 503 by generating a virtual model of the patient's innate anatomical structure (also called “preoperative anatomical structure”). The virtual model may be based on the image data contained within the patient dataset received in step 502. For example, the same computer system that received the patient dataset in step 502 can analyze the image data within the patient dataset to generate a virtual model of the patient's innate anatomical structure. The virtual model may be a two-dimensional or three-dimensional visual representation of the patient's innate biological structure. The virtual model may include one or more regions of interest and may include some or all of the patient's biological structure within the regions of interest (e.g., any combination of tissue types including, but not limited to, bone structure, cartilage, soft tissue, vascular tissue, nerve tissue, etc.). As a non-limiting example, the virtual model may include a virtual representation of the patient's spinal cord region, including some or all of the sacrum, lumbar region, thoracic region, and / or cervical region. In some embodiments, the virtual model includes soft tissue, cartilage, and other non-bone structures. In other embodiments, the virtual model includes only the patient's bone structure. Examples of virtual models of innate anatomical structures are described below with reference to Figures 8A and 8B. In some embodiments, Method 500 can optionally omit the step of generating a virtual model of the patient's innate biological structure in step 503 and proceed directly from step 502 to step 504.

[0082] In some embodiments, the computer system that generated the virtual model in step 502 can determine (e.g., automatically determine or measure) one or more disease metrics for the patient based on the virtual model. For example, the computer system can analyze the virtual model to determine the patient's preoperative lumbar lordosis, Cobb angle, coronal parameters (e.g., coronal balance, global coronal balance, coronal plane pelvic tilt, etc.), sagittal parameters (e.g., pelvic incidence angle, sacral tilt, thoracic kyphosis angle, etc.), and / or pelvic parameters. The disease metrics may include microscopic measurements (e.g., metrics relating to specific or individual connections of the patient's spine) and / or macroscopic measurements (e.g., metrics relating to multiple connections of the patient's spine).

[0083] Method 500 can be continued in step 504 by generating a virtual model of the corrective anatomical configuration for the patient (which may also be referred to herein as the “planned configuration,” “optimal shape,” “postoperative anatomical configuration,” or “target outcome”). For example, a computer system can use the analysis procedure described above to determine a “corrective” or “optimal” anatomical configuration for a particular patient that represents an ideal surgical outcome for that particular patient. This determination can be made, for example, by analyzing multiple reference patient datasets to identify postoperative anatomical configurations for similar patients who had favorable postoperative outcomes, as previously described in detail with respect to Figures 1 to 4C (e.g., based on the similarity of the reference patient dataset to the patient dataset and / or whether the reference patient had a favorable treatment outcome). This identification may include a step of applying one or more mathematical rules (e.g., positional relationships between anatomical elements) and / or target (e.g., acceptable) postoperative metrics / design criteria to determine the optimal anatomical outcome (e.g., adjusting biomimetic structures such as the postoperative sagittal vertical axis being shorter than 7 mm and the postoperative Cobb angle being less than 10 degrees). Target postoperative metrics may include, but are not limited to, target coronal parameters, target sagittal parameters, target pelvic angle of incidence, target Cobb angle, target shoulder inclination, target iliopsoas angle, target coronal equilibrium, target Cobb angle, target lordosis angle, and / or target intervertebral space height. The difference between the innate anatomical configuration and the corrected anatomical configuration may be referred to as "patient-specific correction" or "targeted correction."

[0084] With the corrected anatomical configuration determined, the computer system can generate a two-dimensional or three-dimensional visual representation of the patient's biological structure with the corrected anatomical configuration. Similar to the virtual model generated in step 503, the virtual model of the patient's corrected anatomical configuration may include one or more regions of interest and may include some or all of the patient's biological structures within the regions of interest (e.g., any combination of tissue types including, but not limited to, bone structures, cartilage, soft tissue, vascular tissue, nerve tissue, etc.). As a non-limiting example, the virtual model may include a virtual representation of the spinal region of the patient in a corrected anatomical configuration that includes some or all of the sacrum, lumbar region, thoracic region, and / or cervical region. In some embodiments, the virtual model includes soft tissue, cartilage, and other non-bone structures. In other embodiments, the virtual model includes only the patient's bone structures. Examples of virtual models of innate anatomical configurations are described below with reference to Figures 9A-1 to 9B-2.

[0085] Method 500 can be continued by generating (e.g., automatically generating) a surgical plan to achieve the corrective anatomical configuration shown in the virtual model in step 506. The surgical plan may include a preoperative plan, surgical plan, postoperative plan, and / or specific spinal metrics relating to the optimal surgical outcome. For example, the surgical plan may include specific surgical procedures to achieve the corrective anatomical configuration. In the context of spinal surgery, the surgical plan may include specific fusion surgeries (e.g., PLIF, ALIF, TLIF, LLIF, DLIF, XLIF, etc.) across a specific range of vertebral levels (e.g., L1-L4, L1-5, L3-T1). Naturally, other surgical procedures, such as non-fusion surgical techniques and orthopedic procedures for other parts of the patient, may be identified to achieve the corrective anatomical configuration. The surgical plan may include one or more expected spinal metrics (e.g., lumbar lordosis, Cobb angle, coronal parameter, sagittal parameter, and / or pelvic parameter) corresponding to the expected postoperative patient biomimetic structure. The surgical plan can be generated by the same or a different computer system that generated the virtual model of the corrective anatomical structure. In some embodiments, the surgical plan can be based on one or more reference patient datasets, as described above with respect to Figures 1 to 4C. In some embodiments, the surgical plan can be based at least in part on the surgeon's specific preferences and / or outcomes for the particular surgeon performing the surgery. In some embodiments, more than one surgical plan is generated in step 506 to provide the surgeon with multiple options. An example of a surgical plan is described below with respect to Figure 10.

[0086] After a virtual model of the corrective anatomical structure is generated in step 504 and a surgical plan is generated in step 506, method 500 can continue by transmitting the virtual model of the corrective anatomical structure and the surgical plan for the surgeon's review in step 508. In some embodiments, the virtual model and surgical plan are transmitted as a surgical plan report, an example of which is illustrated with reference to Figure 11. In some embodiments, the same computer system used in steps 502-506 can transmit the virtual model and surgical plan to a computer device for the surgeon's review (e.g., client computer device 102 as described in Figure 1 or computer device 602 as described below with reference to Figure 6). This transmission may include steps of directly transmitting the virtual model and surgical plan to the computer device or uploading the virtual model and surgical plan to a cloud or other storage system for subsequent download. While step 508 describes the step of transmitting the surgical plan and virtual model to the surgeon, those skilled in the art will recognize from the disclosure herein that the surgical plan transmitted to the surgeon may include an image of the virtual model and does not need to include the actual model (e.g., to reduce the size of the transmitted file). Furthermore, the information transmitted to the surgeon in step 508 may include a virtual model (or image thereof) of the patient's innate anatomical structure in addition to a virtual model of the corrective anatomical structure. In embodiments in which more than one surgical plan is generated in step 506, method 500 may include a step of transmitting more than one surgical plan to the surgeon for review and selection.

[0087] The surgeon reviews the virtual model and surgical plan and, in step 510, either approves or rejects the surgical plan (or, if more than one surgical plan is provided in step 508, selects one of the provided surgical plans). If the surgeon does not approve the surgical plan in step 510, the surgeon may optionally provide feedback and / or suggestions for modifications to the surgical plan (e.g., by adjusting the virtual model or changing one or more aspects of the plan). Thus, method 500 may include a step of receiving the surgeon's feedback and / or modification suggestions (e.g., by a computer system). If the surgeon's feedback and / or modification suggestions are received in step 512, method 500 may continue in step 514 by correcting the virtual model and / or surgical plan at least in part based on the surgeon's feedback and / or modification suggestions received in step 512 (e.g., automatically corrected by a computer system). In some embodiments, the surgeon does not provide feedback and / or modification suggestions if they reject the surgical plan. In such embodiments, step 512 may be omitted, and method 500 may continue by correcting the virtual model and / or surgical plan in step 514 by selecting a new and / or additional reference patient dataset (e.g., automatically corrected by a computer system). The corrected virtual model and / or surgical plan may then be sent to the surgeon for review. Steps 508, 510, 512, and 514 may be repeated as many times as necessary until the surgeon approves the surgical plan. While it has been described that the surgeon reviews, modifies, approves, and / or rejects the surgical plan, in some embodiments the surgeon may review, modifies, approve, and / or reject the corrective anatomical configuration shown by the virtual model.

[0088] With surgical approval of the surgical plan received in step 510, method 500 can proceed in step 516 by designing a patient-specific implant based on the corrective anatomical configuration and surgical plan (e.g., using the same computer system used to perform steps 502-514). For example, a patient-specific implant can be specifically designed to induce the patient's biostructure to assume a corrective anatomical configuration when implanted in a particular patient (e.g., deforming the patient's biostructure from its innate anatomical configuration to a corrective anatomical configuration). A patient-specific implant can be designed to cause the patient's biostructure to assume a corrective anatomical configuration for the expected lifespan of the implant (e.g., 5 years or longer, 10 years or longer, 20 years or longer, 50 years or longer, etc.) when implanted. In some embodiments, the patient-specific implant is designed based solely on a virtual model of the corrective anatomical configuration and / or without reference to preoperative patient images.

[0089] A patient-specific implant may be one or more of the implants described herein or any of the patent references incorporated herein by reference. For example, a patient-specific implant may include one or more of the following: screws (e.g., bone screws, spinal screws, vertebral arc root screws, facet screws), intervertebral implantation devices (e.g., intervertebral implants), cages, plates, rods, discs, fixation devices, spacers, rods, expandable devices, stents, brackets, cords, scaffolds, anchoring devices, anchors, nuts, bolts, rivets, connectors, tethers, fasteners, joint replacements (e.g., artificial intervertebral discs), or hip joint implants. A patient-specific implant design may include data representing one or more of the physical properties of the implant (e.g., size, shape, volume, material, mass, weight), mechanical properties (e.g., stiffness, strength, modulus of elasticity, hardness), and / or biomimetic properties (e.g., osseointegration, cell adhesion, antibacterial properties, antiviral properties). For example, the design of an orthopedic implant may include the shape, size, material, and / or effective stiffness of the implant (e.g., lattice density, number of struts, strut placement, etc.). An example of a patient-specific implant designed by Method 500 is described below with reference to Figures 12A and 12B.

[0090] In some embodiments, the step of designing the implant in step 516 may optionally include a step of generating a manufacturing command for manufacturing the implant. For example, the computer system may generate a computer-executable manufacturing command that, when executed by the manufacturing system, causes the manufacturing system to manufacture the implant.

[0091] In some embodiments, the patient-specific implant is designed in step 516 only after the surgeon has reviewed and approved the virtual model along with the orthodontic anatomical configuration and surgical plan. Thus, in some embodiments, the implant design is not sent to the surgeon along with the surgical plan in step 508, nor is it manufactured before receiving surgical approval of the surgical plan. By not being bound by theory and waiting for the surgeon to approve the surgical plan before designing the patient-specific implant, the efficiency of method 500 can be increased and / or the resources required to implement method 500 can be reduced.

[0092] Method 500 can be continued by manufacturing a patient-specific implant in step 518. The implant may be manufactured using additive manufacturing techniques such as 3D printing, stereolithography, digital photoprocessing, fusion deposition modeling, selective laser sintering, selective laser melting, electron beam melting, laminated material manufacturing, powder bed printing, thermoplastic printing, direct material deposition, or inkjet photopolymer printing, or similar techniques, or a combination thereof. Alternatively or in addition thereto, the implant may be manufactured using subtractive manufacturing techniques such as CNC fabrication, electrical discharge manufacturing (EDM), grinding, laser cutting, waterjet fabrication, manual fabrication (e.g., milling, turning), or similar techniques, or a combination thereof. The implant may be manufactured by any suitable manufacturing system (e.g., manufacturing system 124 shown in Figure 1 or manufacturing system 630 described below with respect to Figure 6). In some embodiments, the implant is manufactured by a manufacturing system that executes computer-readable manufacturing instructions generated by a computer system in step 516.

[0093] With the implant manufactured in step 518, method 500 can continue by implanting the patient-specific implant into the patient in step 520. The surgical procedure can be performed manually, by a robotic surgical platform (e.g., a surgical robot), or a combination thereof. In embodiments in which the surgical procedure is performed at least partially by a robotic surgical platform, the surgical plan may include computer-readable control instructions configured to cause the surgical robot to perform at least partially the patient-specific surgical procedure. Additional details regarding the robotic surgical platform are described below with reference to Figure 6.

[0094] Method 500 can be implemented and executed in various ways. In some embodiments, steps 502-516 can be implemented by a computer system associated with a first entity (e.g., computer system 606 as described below with reference to Figure 6), step 518 can be implemented by a manufacturing system associated with a second entity, and step 520 can be implemented by a surgical provider, surgeon, and / or robotic surgical platform associated with a third entity. Any of the steps described above can be implemented as computer-readable instructions stored in memory and executable by one or more processors of the associated computer system.

[0095] Figure 6 is a schematic diagram of a surgical environment including typical systems and devices that can be used to provide patient-specific medical care, such as for performing Method 500 as described in relation to Figure 5. As shown in the diagram, the surgical environment includes a computer device 602, a computer system 606, a cloud 608, a manufacturing system 630, and a robotic surgical platform 650. The computer device 602 can be a user device such as a smartphone, mobile device, laptop, desktop, personal computer, tablet, phablet, or other such device known in the art. During surgery, the user (e.g., surgeon) can use the computer device 602 to collect, retrieve, examine, modify, or otherwise interact with patient datasets. The computer system 606 may include any suitable computer system configured to store one or more software modules for tasks such as identifying a reference patient dataset, determining a patient-specific surgical plan, generating a virtual model of the patient's biostructure, or designing a patient-specific implant. The one or more software modules may include algorithms, machine learning models, or artificial intelligence architectures for performing typical operations. Cloud 608 can be any suitable network and / or storage system and may include any combination of hardware and / or virtual computing resources. Manufacturing system 630 can be any suitable manufacturing system for manufacturing patient-specific implants, including any of those described herein. Robotic surgical platform 650 (hereinafter referred to as "Platform 650") can be configured to perform or assist one or more aspects of a surgical procedure.

[0096] In a typical surgical procedure, patient-specific medical care can be provided, such as performing the method 500 described with respect to Figure 5 using a computer device 602, a computer system 606, a cloud 608, a manufacturing system 630, and a platform 650. For example, the computer system 606 can receive a patient dataset from the computer device 602 (e.g., step 502 of method 500). In some embodiments, the computer device 602 can directly transmit the patient dataset to the computer system 606. In other embodiments, the computer device 602 can upload the patient dataset to the cloud 608, and the computer system 606 can download the patient dataset from the cloud or otherwise access it. With the patient dataset in hand, the computer system 606 can generate a virtual model of the patient's innate anatomical structure (e.g., step 503 of method 500), generate a virtual model of a corrective anatomical structure (e.g., step 504 of method 500), and / or generate a surgical plan to achieve the corrective anatomical structure (e.g., step 506 of method 500). In some embodiments, the computer system may perform the operations described above by one or more software modules, including a machine learning model or other artificial intelligence architecture. With the virtual model and surgical plan generated, the computer system 606 may transmit the virtual model and surgical plan to the surgeon for review (e.g., step 508 of method 500). This transmission may include, for example, a step of directly transmitting the virtual model and surgical plan to the computer device 602 for the surgeon's review. In other embodiments, this transmission may include a step of uploading the virtual model and surgical plan to the cloud 608. The surgeon can then download the virtual model and surgical plan from the cloud 608 using the computer device 602 or otherwise access it.

[0097] The surgeon can use computer device 602 to review the virtual model and surgical plan. Similarly, the surgeon can approve or reject the surgical plan and provide any feedback regarding the surgical plan using computer device 602. The surgeon's approval, rejection, and / or feedback regarding the surgical plan can be transmitted to computer system 606, which can receive it (e.g., steps 510 and 512 of method 500). The computer system 606 can then correct the virtual model and / or surgical plan (e.g., step 514 of method 500). The computer system 606 can then transmit the corrected virtual model and surgical plan to the surgeon for review (e.g., by uploading it to cloud 608 or by transmitting it directly to computer device 602).

[0098] The computer system 606 can design a patient-specific implant using one or more software modules based on the orthodontic anatomical configuration and surgical plan (e.g., step 516 of method 500). In some embodiments, the software modules rely on one or more algorithms, machine learning models, or other artificial intelligence architectures to design the implant. Once the patient-specific implant is designed, the computer system 606 can upload this design and / or manufacturing instruction to the cloud 608. Similarly, the computer system 606 can generate manufacturing instructions (e.g., computer-readable manufacturing instructions) for manufacturing the patient-specific implant. In such embodiments, the computer system 606 can upload the manufacturing instructions to the cloud 608.

[0099] The manufacturing system 630 can download or otherwise access design and / or manufacturing instructions for a patient-specific implant from the cloud 608. The manufacturing system can then manufacture the patient-specific implant using additive manufacturing techniques, subtractive manufacturing techniques, or other appropriate manufacturing techniques (e.g., step 518 in method 500).

[0100] The robotic surgical platform 650 can perform or otherwise assist in one or more aspects of a surgical procedure (step 520 of method 500). For example, the platform 650 can provide tissue for incision, perform incision, perform excision, remove tissue, manipulate tissue, perform corrective operations, deliver implants to a target site, place implants at a target site, adjust implants at a target site, manipulate implants after implantation, fix implants at a target site, remove implants, suture tissue, etc. Accordingly, the platform 650 may include one or more arms 655 and end effectors intended for holding various surgical tools (e.g., grasping forceps, clips, needles, needle holders, irrigation tools, suction tools, anastomotics, screwdriver assemblies, etc.), imaging instruments (e.g., cameras, sensors, etc.), and / or medical devices (e.g., implants 600), enabling the platform 650 to perform one or more aspects of a surgical plan. Although shown as having one arm 655, those skilled in the art will recognize that the platform 650 can have multiple (e.g., two, three, four, or five or more) arms and any number of joints, linkages, motors, and degrees of freedom. In some embodiments, the platform 650 may have a first arm dedicated to holding one or more imaging instruments, while the remaining arms hold various surgical tools. In some embodiments, these tools can be removably attached to the arms so that they can be selectively replaced before, during, or after a surgical procedure. The arms can be moved through a variety of ranges of motion (e.g., degrees of freedom) to provide sufficient dexterity to perform various aspects of a surgical procedure.

[0101] The platform 650 may include a control module 660 for controlling the movement of the arm 655. In some embodiments, the control module 660 includes a user input device (not shown) for controlling the movement of the arm 655. The user input device may be a joystick, mouse, keyboard, touch screen, infrared sensor, touchpad, wearable input device, camera or image-based input device, microphone, or other user input device. A user (e.g., a surgeon) can interact with the user input device to control the movement of the arm 655.

[0102] In some embodiments, the control module 660 includes one or more processors for executing machine-readable action commands that automatically control the movement of the arm 655 to perform one or more aspects of a surgical procedure when executed. In some embodiments, the control module 660 can receive machine-readable action commands (e.g., from the cloud 608) that specify one or more stages of a surgical procedure and cause the platform 650 to perform these stages when executed by the control module 660. For example, a machine-readable action command could instruct the platform 650 to perform actions such as providing tissue for incision, making an incision, performing an excision, removing tissue, manipulating tissue, performing a corrective operation, delivering the implant 600 to a target site, placing the implant 600 at the target site, adjusting the configuration of the implant 600 at the target site, manipulating the implant 600 after it has been implanted, fixing the implant 600 at the target site, removing the implant 600, suturing tissue, etc. Therefore, the actuation command may include specific commands to articulate arm 655 to perform or otherwise assist in the delivery of a patient-specific implant.

[0103] In some embodiments, the platform 650 can generate machine-readable action commands based on the surgical plan (rather than simply receiving them). For example, the surgical plan may include information about the delivery route, delivery tools, and implantation site. The platform 650 can analyze the surgical plan and develop executable action commands to perform patient-specific procedures based on the functions of the robotic system (e.g., configuration and number of robotic arms, functions of end effectors, guidance systems, visualization systems, etc.). This makes it possible to adapt the surgical environment shown in Figure 6 to a wide variety of robotic surgical systems.

[0104] Platform 650 may include one or more communication devices (e.g., components with VLC, WiMax, LTE, WLAN, IR communication, PSTN, radio waves, Bluetooth, and / or Wi-Fi capabilities) to establish a connection with Cloud 608 and / or Computer Device 602 to access and / or download surgical plans and / or machine-readable operation instructions. For example, Cloud 608 may receive a request from Platform 650 for a specific surgical plan and send this plan to Platform 650. Having identified the surgical plan, Cloud 608 may send it directly to Platform 650 for execution. In some embodiments, Cloud 608 may send the surgical plan to one or more intermediate network devices (e.g., Computer Device 602) instead of sending it directly to Platform 650. The user may use Computer Device 602 to review the surgical plan before sending it to Platform 650 for execution. Further details regarding the identification, storage, downloading, and access to patient-specific surgical plans are described in U.S. Patent Application No. 16 / 990,810, filed August 11, 2020, the entire disclosure of which is incorporated herein by reference.

[0105] Platform 650 may include additional components not explicitly shown in Figure 6. For example, in various embodiments, Platform 650 may include one or more displays (e.g., LCD display screens, LED display screens, projection displays, holographic displays, or augmented reality displays (e.g., head-up display devices or head-mounted devices)), one or more I / O devices (e.g., network cards, video cards, audio cards, USB, FireWire or other external devices, cameras, printers, speakers, CD-ROM drives, DVD drives, disk drives, or Blu-ray devices), and / or memory (e.g., random access memory (RAM), various caches, CPU registers, read-only memory (ROM), and writable non-volatile memory, such as flash memory, hard drives, floppy disks, CDs, DVDs, magnetic storage devices, tape drives, or device buffers). In some embodiments, the above-described components may be substantially similar to similar components described in detail with respect to the computer device 200 in Figure 2.

[0106] Without being bound by theory, using a robotic surgical platform to implement various aspects of the surgical plans described herein is expected to bring several advantages over conventional surgical techniques. For example, the use of a robotic surgical platform can improve surgical outcomes and / or shorten recovery time by, for example, reducing the size of the incision, reducing blood loss, shortening the length of the surgical procedure, increasing the precision and accuracy of the surgery (e.g., placement of implants at the target site). Similarly, platform 650 can avoid or reduce user input errors by, for example, including one or more scanners for acquiring information from instruments (e.g., instruments with retrieval capabilities), tools, and patient-specific implants 600 (e.g., after being grasped by arm 655). Platform 650 can verify the use of the correct instruments before and during the surgical procedure. If platform 650 identifies an incorrect instrument or tool, it can send a warning to the user that another instrument or tool must be fitted. The user can scan the new instrument to confirm that it is suitable for the surgical plan. In some embodiments, the surgical plan includes instructions for use, a list of instruments, instrument specifications, or replacement parts for instruments. The platform 650 can perform pre- and post-operative examination routines based on information from the scanner.

[0107] Figures 7A to 13 further illustrate, for example, a selection mechanism for providing patient-specific medical care according to Method 500. For example, Figures 7A to 7D illustrate an example of a patient dataset 700 (for example, received in step 502 of Method 500). The patient dataset 700 may include any of the information described above with respect to the patient dataset. For example, the patient dataset 700 includes patient information 701 (e.g., patient identification number, patient MRN, patient name, sex, age, body mass index (BMI), surgical data, surgeon, etc., as shown in Figures 7A and 7B), diagnostic information 702 (e.g., Oswestry disability index (ODI), VAS back score, VAS leg score, preoperative pelvic angle of incidence, preoperative lumbar lordosis, preoperative PI-LL angle, preoperative lumbar coronal Cobb angle, etc., as shown in Figures 7B and 7C), and image data 703 (e.g., X-ray, CT, MRI, etc., as shown in Figure 7D). In the illustrated embodiment, the patient dataset 700 is collected by a healthcare provider (e.g., a surgeon, nurse, etc.) using a digital report and / or fillable report accessible via a computer device (e.g., computer device 602 shown in Figure 6). In some embodiments, the patient dataset 700 can be generated automatically or at least partially automatically based on the patient's digital medical records. In any case, once collected, the patient dataset 700 can be transmitted to a computer system (e.g., computer system 606 shown in Figure 6) configured to generate a surgical plan for the patient.

[0108] Figures 8A and 8B illustrate an example of a virtual model of a patient's innate anatomical structure (e.g., one that occurs in step 503 of method 500). In particular, Figure 8A is a magnified view of the virtual model 800 of the patient's innate biostructure, illustrating the innate biostructure of the patient's lower spinal cord region. The virtual model 800 is a three-dimensional visual representation of the patient's innate biostructure. In the illustrated embodiment, the virtual model includes a portion of the spine extending from the sacrum to the L4 vertebral level. Naturally, the virtual model may include other regions of the patient's spine, including the cervical vertebrae, thoracic vertebrae, lumbar vertebrae, and sacrum. While the illustrated virtual model 800 includes only the bone structure of the patient's biostructure, other embodiments may include additional structures such as cartilage, soft tissue, vascular tissue, and nerve tissue.

[0109] Figure 8B shows a virtual model display 850 (hereinafter referred to as “Display 850”) showing various images of the virtual model 800. The virtual model display 850 includes a three-dimensional image of the virtual model 800, one or more coronal sections 802 of the virtual model 800, one or more axial sections 804 of the virtual model 800, and / or one or more sagittal sections 806 of the virtual model 800. Naturally, other images are possible and can be included on the virtual model display 850. In some embodiments, the virtual model 800 can be made interactive so that the user can manipulate the orientation or line of sight of the virtual model 800 (e.g., rotate it), change the depth of the display sections, or select and isolate specific bone structures.

[0110] Figures 9A-1 to 9B-2 specify examples of virtual models of the patient's congenital anatomical structure (e.g., occurring in step 503 of Method 500) and virtual models of the patient's corrected anatomical structure (e.g., occurring in step 504 of Method 500). In particular, Figures 9A-1 and 9A-2 are anterior and lateral views of virtual model 910 showing the patient's congenital anatomical structure, respectively, and Figures 9B-1 and 9B-2 are anterior and lateral views of virtual model 920 showing the corrected anatomical structure for the same patient, respectively. Referring first to Figure 9A-1, the anterior view of virtual model 910 shows that the patient has an abnormal curvature of the spine (e.g., scoliosis). This abnormal curvature is marked by a line X along the body axis of the spine. Next, referring to Figure 9A-1, a lateral view of virtual model 910 shows that the patient has a collapsed or narrowed intervertebral disc between adjacent vertebral endplates, marked by an ellipse Y. Figures 9B-1 and 9B-2 show a corrected virtual model 920 that takes into account the abnormal anatomical configuration shown in Figures 9A-1 and 9A-2. For example, Figure 9B-1, an anterior view of virtual model 920, shows the spine of a patient with a corrected configuration (reduced abnormal curvature). This correction is also indicated by line X, which runs along the body axis of the spine. Figure 9B-2, a lateral view of virtual model 920, shows the spine of a patient with recovered intervertebral disc height (widened intervertebral space between adjacent vertebral endplates), also marked by an ellipse Y. Line X and ellipse Y are presented to more clearly illustrate the correction between virtual models 910 and 920 in Figures 9A-1 to 9B-2 and are not necessarily included on virtual models generated according to the art of the present invention.

[0111] Figure 10 shows an example of a surgical plan 1000 (e.g., one that occurs in step 506 of method 500). The surgical plan 1000 may include a preoperative patient metric 1002, a predicted postoperative patient metric 1004, one or more patient images (e.g., patient images 703 received as part of a patient dataset), a virtual model 910 of the patient's innate anatomical structure (e.g., preoperative patient biostructure) (which may be the model itself or one or more images derived from the model), and / or a virtual model 920 of the patient's corrective anatomical structure (e.g., predicted postoperative patient biostructure) (which may be the model itself or one or more images derived from the model). The virtual model 920 of the predicted postoperative patient biostructure may optionally include one or more implants 1012 shown as embedded within the patient's spinal cord region to specify how the patient's biostructure will look following surgery. While the virtual model 920 shows four implants 1012, the surgical plan 1000 may include more or fewer implants 1012, including 1, 2, 3, 5, 6, 7, 8, or 9 or more implants 1012.

[0112] The surgical plan 1000 may include additional information beyond what is shown in Figure 10. For example, the surgical plan 1000 may include preoperative instructions, surgical instructions, and / or postoperative instructions. The surgical instructions may include one or more specific steps to be performed (e.g., PLIF, ALIF, TLIF, LLIF, DLIF, XLIF, etc.) and / or one or more specific surgical targets (e.g., fixation of vertebral levels L1-L4, securing screws so that they are inserted into the outer surface of L4, etc.). Although Figure 10 specifies the surgical plan 1000 as a visual report, the surgical plan 1000 may be encoded in computer-executable instructions that, when executed by a processor connected to a computer device, cause the surgical plan 1000 to be displayed by the computer device. In some embodiments, the surgical plan 1000 may include machine-readable action instructions for performing it. For example, the surgical plan may include action instructions for a robotic surgical platform to perform one or more stages of the surgical plan 1000.

[0113] Figure 11 provides a series of images showing an example of a patient surgical plan report 1100, which includes a surgical plan 1000 and can be sent to the surgeon for review and approval (as sent in step 508 of Method 500). The surgical plan report 1100 may include a multi-page report detailing aspects of the surgical plan 1000. For example, a multi-page report may include a first page 1101 specifying an outline of the surgical plan 1000 (e.g., shown in Figure 10), a second page 1102 showing a patient image (e.g., patient image 703, received in step 502 and shown in Figure 7D), a third page 1103 showing a magnified view of a virtual model of the corrective anatomical configuration (e.g., virtual model 920, shown in Figure 9), and a fourth page 1104 prompting the surgeon to either approve or reject the surgical plan 1000. Naturally, additional information regarding the surgical plan can be provided with the report 1100 in the same or different format. In some embodiments, if the surgeon rejects the surgical plan 1000, the surgeon may be prompted to provide feedback on aspects of the surgical plan 1000 that the surgeon would like to modify.

[0114] The patient surgical plan report 1100 can be presented to the surgeon on a digital display of a computer device (e.g., the client computer device 102 shown in Figure 1 or the computer device 602 shown in Figure 6). In some embodiments, the report 1100 is interactive, allowing the surgeon to manipulate various aspects of the report 1100 (e.g., adjust the image of a virtual model, zoom in, zoom out, add annotations, etc.). However, even when the report 1100 is interactive, the surgeon generally cannot directly modify the surgical plan 1000. Instead of directly modifying it, the surgeon can provide feedback and proposed changes to the surgical plan 1000, which can then be sent back to the computer system that generated the surgical plan 1000 for analysis and improvement.

[0115] Figure 12A shows an example of a patient-specific implant 1200 (e.g., designed in step 516 of Method 500 and manufactured in step 518), and Figure 12B shows the implant 1200 implanted in the patient. The implant 1200 may be any orthopedic implant or other implant specifically designed to guide the patient's body to conform to the orthodontic anatomical configuration described above. In the illustrated embodiment, the implant 1200 is an intervertebral device having a first (e.g., upper) surface 1202 configured to engage with the lower endplate surface of the upper vertebral body and a second (e.g., lower) surface 1204 configured to engage with the upper endplate surface of the lower vertebral body. The first surface 1202 may have a patient-specific morphology designed to conform (e.g., interlock) to the morphology of the lower endplate surface of the upper vertebral body to form a substantially gapless joint surface between them. Similarly, the second surface 1204 may have a patient-specific morphology designed to conform to or interlock to the morphology of the upper endplate surface of the lower vertebral body to form a substantially gapless joint surface between them. The implant 1200 may include a recess 1206 or other feature configured to facilitate endoosseous growth. Since the implant 1200 is patient-specific and designed to induce geometric changes within the patient, it is not necessarily symmetrical and is often asymmetrical. For example, in the illustrated embodiment, the implant 1200 has an uneven thickness such that the plane defined by the first surface 1202 is not parallel to the central longitudinal axis A of the implant 1200. Naturally, since the implants described herein, including implant 1200, are patient-specific, the art of the present invention is not limited to any particular implant design or implant characteristics. Additional features of patient-specific implants that can be designed and manufactured according to the art of the present invention are described in U.S. Patent Applications No. 16 / 987,113 and No. 17 / 100,396, the full disclosures of these documents are incorporated herein by reference.

[0116] The patient-specific medical procedures described herein may include steps involving the implantation of more than one patient-specific implant within the patient to achieve corrective anatomical configuration (multi-site procedures). For example, Figure 13 shows a lower spinal cord region with three patient-specific implants 1300a–1300c implanted at different vertebral levels. More specifically, the first implant 1300a is implanted between the L3 and L4 vertebral bodies, the second implant 1300b is implanted between the L4 and L5 vertebral bodies, and the third implant 1300c is implanted between the L5 vertebral body and the sacrum. Together, the implants 1300a–1300c can cause the patient's spinal cord region to adopt a previously identified anatomical configuration (deforming the patient's biostructure from a preoperative pathological configuration to an optimal postoperative configuration). In some embodiments, more or fewer implants are used to achieve corrective anatomical configuration. For example, in some embodiments, one, two, four, five, six, seven, eight, or nine or more implants are used to achieve corrective anatomical configuration. In embodiments requiring more than one implant, the implants may not necessarily have the same shape, size, or function. In fact, multiple implants will often have different shapes and forms corresponding to the target vertebral levels in which they will be implanted. As also shown in Figure 13, the patient-specific medical procedures described herein may include steps to treat the patient in multiple target areas (e.g., multiple vertebral levels).

[0117] In addition to designing patient-specific medical care based on a baseline patient dataset, the systems and methods of the present invention can design patient-specific medical care based on disease progression for a particular patient. Accordingly, in some embodiments, the technology of the present invention includes a software module (e.g., a machine learning model or other algorithm) that can be used to analyze, predict, and / or model disease progression for a particular patient. The machine learning model can be trained on multiple baseline patient datasets, which include disease progression metrics for each of the baseline patients in addition to the patient data described with respect to Figure 1. Progression metrics may include measurements of disease metrics over a period of time. Appropriate metrics may include spinal-pelvic parameters (e.g., lumbar lordosis, pelvic tilt, sagittal plane vertical axis (SVA), Cobb angle, coronal plane offset, etc.), disability scores, functional function scores, flexibility scores, or VAS pain scores. Progression of metrics for each baseline patient can be correlated with other patient information for such a particular baseline patient (e.g., age, sex, height, weight, activity level, diet, etc.).

[0118] In some embodiments, the technology of the present invention includes a disease progression module comprising an algorithm, machine learning model, or other software analysis tool for predicting disease progression in a particular patient. The disease progression module can be trained on a reference patient dataset that includes patient information (e.g., age, sex, height, weight, activity level, diet, etc.) and disease metrics (e.g., diagnosis, spinal-pelvic parameters such as lumbar lordosis, pelvic tilt, sagittal plane vertical axis, Cobb angle, coronal plane offset, disability score, functional function score, flexibility score, VAS pain score, etc.). Disease metrics may include values ​​over a period of time. For example, reference patient data may include disease metric values ​​daily, weekly, monthly, bimonthly, yearly, or for other criteria. By measuring these metrics over a period of time, changes in metric values ​​can be tracked as estimates of disease progression and correlated with other patient data.

[0119] Accordingly, in some embodiments, the disease progression module can estimate the rate of disease progression for a particular patient. This progression can be estimated by achieving an estimated change in one or more disease metrics over a period of time (e.g., an X% increase in the disease metric each year). This rate may be constant (e.g., a 5% increase in pelvic tilt each year) or variable (e.g., a 5% increase in pelvic tilt in the first year, a 10% increase in pelvic tilt in the second year, etc.). In some embodiments, this estimate can be sent to a surgeon or other healthcare provider who can review the estimated rate of progression and update it as needed.

[0120] As a non-limiting example, a specific patient, a 55-year-old male, may have an SVA value of 6 mm. The disease progression module can analyze the patient reference dataset to identify disease progression in individual reference patients who have one or more similarities to this specific patient (e.g., individual reference patients who have an SVA value of approximately 6 mm, are nearly the same age, weight, height, and / or are of the same sex as the patient in question). Based on this analysis, the disease progression module can predict the rate of disease progression in the absence of surgical intervention (e.g., the patient's VAS pain score may increase by 5%, 10%, or 15% annually in the absence of surgical intervention, or the SVA value may continue to increase by 5% annually in the absence of surgical intervention).

[0121] The systems and methods described herein can generate models / simulations based on estimated disease progression rates, thereby modeling various outcomes over a desired period. In addition, the models / simulations can predict the patient's overall health or mobility, etc., by considering any number of additional diseases or conditions. These additional diseases or conditions can be used in combination with other patient health factors (e.g., height, weight, age, activity level, etc.) to generate a patient health score that reflects the patient's overall health. The patient health score can be displayed for surgical review and / or incorporated into the disease progression estimation. Accordingly, the technology of the present invention can generate one or more virtual simulations of expected disease progression to specify how the patient's biostructure is expected to change over time. Physician input can be used to generate or modify the virtual simulations. The technology of the present invention can generate one or more post-treatment virtual simulations based on received physician input for review by healthcare providers, patients, etc.

[0122] In some embodiments, the technology of the present invention can predict, model, and / or simulate disease progression based on one or more potential surgical interventions. For example, the disease progression module can simulate how a patient's biostructure might look at 1, 2, 5, or 10 years postoperatively for several surgical intervention options. The simulations can incorporate non-surgical factors such as the patient's age, height, weight, sex, activity level, or other health conditions, as described above. Based on these simulations, the system and / or surgeon can select which surgical intervention is best suited for long-term effects. These simulations can be used to determine patient-specific corrections to compensate for expected disease progression.

[0123] Accordingly, in some embodiments, multiple (e.g., 2, 3, 4, 5, 6, or 7 or more) disease progression models are simulated to obtain disease progression data for several different surgical intervention options or other scenarios. For example, the disease progression module may generate models predicting postoperative disease progression for each of three different surgical interventions. A surgeon or other healthcare provider can then scrutinize the disease progression models and, based on this scrutiny, select which of the three surgical interventions is most likely to provide the best long-term outcome for the patient. Naturally, the step of selecting the optimal intervention can be fully automated or semi-automated, as described herein.

[0124] Based on modeled disease progression, the systems and methods described herein can (i) identify the optimal timing for surgical intervention and / or (ii) identify the optimal type of surgical procedure for a patient. Accordingly, in some embodiments, the technology of the present invention includes an intervention timing module comprising an algorithm, machine learning model, or other software analysis tool for determining the optimal timing for surgical intervention in a particular patient. This can be done, for example, by analyzing patient reference data including (i) preoperative disease progression metrics for individual reference patients, (ii) disease metrics at the time of surgical intervention for individual reference patients, (iii) postoperative disease progression metrics for individual reference patients, and / or (iv) scored surgical outcomes for individual reference patients. The intervention timing module can compare disease metrics for a particular patient with a reference patient dataset to determine the point in disease progression at which surgical intervention resulted in the most favorable outcome for similar patients.

[0125] As a non-limiting example, a reference patient dataset may include data on the sagittal vertical axis of reference patients. This data may include (i) sagittal vertical axis values ​​for individual patients over the period prior to surgical intervention (e.g., how quickly and to what extent the sagittal vertical axis values ​​changed), (ii) the sagittal vertical axis of individual patients at the time of surgical intervention, (iii) the change in the sagittal vertical axis after surgical intervention, and (iv) the degree of success of the surgical intervention (e.g., based on pain, quality of life, or other factors). Based on the data described above, the intervention timing module can identify, based on the sagittal vertical axis values ​​of a particular patient, at what point in time the surgical intervention is most likely to produce the most favorable outcome. Naturally, the metrics mentioned above are merely illustrative, and the intervention timing module can incorporate other metrics (e.g., lumbar lordosis, pelvic tilt, sagittal plane vertical axis, Cobb angle, coronal plane offset, disability score, functional function score, flexibility score, VAS pain score) in place of or in combination with the sagittal plane vertical axis to predict the time of day when surgical intervention has the highest probability of providing a favorable outcome for a particular patient.

[0126] The intervention timing module can also incorporate one or more mathematical rules based on thresholds for various disease metrics. For example, the intervention timing module may indicate that surgical intervention is necessary if one or more disease metrics exceed predetermined thresholds or if any of the other criteria are met. Typical thresholds indicating that surgical intervention may be necessary include an SVA value greater than 7 mm, a mismatch greater than 10 degrees between lumbar lordosis and pelvic incidence angle, a Cobb angle greater than 10 degrees, and / or a combination of the Cobb angle and LL / PI mismatch greater than 20 degrees. Naturally, other thresholds and metrics can be used, and those described above are merely illustrative and do not limit the disclosure of the present invention. In some embodiments, the rules described above can be tailored to specific patient populations (for example, in men older than 50 years, an SVA value greater than 7 mm indicates the need for surgical intervention). If a particular patient does not exceed the threshold indicating that surgical intervention is recommended, the intervention timing module can provide the patient with an estimate of when the patient's metric will be greater than one or two thresholds, thereby providing the patient with an estimate of when surgical intervention may be recommended.

[0127] The technology of the present invention may include a treatment planning module that can identify the optimal type of surgical procedure for a patient based on the progression of the patient's disease. The treatment planning module may be an algorithm, machine learning model, or other software analysis tool that is trained on or based on multiple reference patient datasets as described above. Furthermore, the treatment planning module may incorporate one or more mathematical rules for identifying surgical procedures. As a non-limiting example, the treatment planning module may recommend anterior fixation when the LL / PI mismatch is between 10 and 20 degrees, but may recommend both anterior and posterior fixation when the LL / PI mismatch is greater than 20 degrees. As another non-limiting example, the treatment planning module may recommend posterior fixation when the SVA value is between 7 mm and 15 mm, but may recommend both posterior and anterior fixation when the SVA is greater than 15 mm. Naturally, other rules may be used, and those described above are merely illustrative and do not limit the disclosure of the present invention.

[0128] Without being bound by theory, the effectiveness of procedures can be further enhanced by incorporating disease progression modeling into patient-specific medical procedures described herein. For example, in many cases, it may be disadvantageous to perform surgery after a patient's disease has progressed to an irreversible or unstable state. However, it may also be disadvantageous to perform surgery too early, before the patient's disease becomes symptomatic and / or when there is no possibility of further progression. Therefore, the disease progression module and / or intervention timing module can help identify the time window in which surgical intervention in a particular patient has the highest probability of producing a favorable outcome for that patient.

[0129] As those skilled in the art will recognize, any of the above-described software modules can be combined into a single software module for performing the operations described herein. Similarly, software modules can be distributed across any combination of computer systems and computer devices described herein, and are not limited to the specific configurations described herein. Accordingly, unless otherwise expressly noted, any of the operations described herein can be performed by any of the computer devices or computer systems described herein.

[0130] The detailed description above illustrates various embodiments of the device and / or process using block diagrams, flowcharts, and / or examples. Those skilled in the art will recognize that, insofar as such block diagrams, flowcharts, and / or examples include one or more functions and / or operations, each function and / or operation within such block diagrams, flowcharts, and / or examples can be implemented individually and / or collectively by a wide range of hardware, software, firmware, or virtually any combination thereof. In some embodiments, some parts of the subject matter described herein can be implemented by application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), or other integrated formats. However, those skilled in the art will recognize that aspects of some embodiments disclosed herein can be uniformly implemented within integrated circuits as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or in virtually any combination thereof, and that the stages of designing the circuits and / or writing the code for the software and / or firmware in light of the disclosure of the present invention are well within the skill of those skilled in the art. Furthermore, those skilled in the art will recognize that the mechanisms of the subject matter described herein have functions that are distributed as program products in various forms, and that the exemplary embodiments of the subject matter described herein are applicable regardless of the particular type of signal-carrying medium used to actually implement this distribution. Examples of signal-carrying media include, but are not limited to, recordable media such as floppy disks, hard disk drives, CDs, DVDs, digital tapes, and computer memory, as well as transmittable media such as digital and / or analog communication media (e.g., optical fiber cables, waveguides, wired communication links, wireless communication links, etc.).

[0131] Those skilled in the art will recognize that it is common in the art to represent devices and / or processes in the types shown herein and then integrate such represented devices and / or processes into a data processing system using engineering practice. That is, at least a portion of the devices and / or processes described herein can be integrated into a data processing system through a reasonable amount of experimentation. Those skilled in the art will recognize that a typical data processing system generally includes one or more of the following: a system unit housing, video display devices, memory such as volatile and non-volatile memory, processors such as microprocessors and digital signal processors, computing entities such as operating systems, drives, graphical user interfaces and application programs, one or more interaction devices such as touchpads or touchscreens, and / or control systems including feedback loops and control motors (e.g., feedback for sensing position and / or velocity, control motors for moving and / or adjusting components and / or quantities). A typical data processing system can be implemented using any suitable commercially available components commonly found in data computer / communication systems and / or network computer / communication systems.

[0132] The subject matter described herein includes various components that may be included in or connected to various other components. It should be acknowledged that the architectures shown are merely examples, and that many other architectures performing the same function can be implemented in practice. Conceptually, any arrangement of components performing the same function is substantially “associated” in such a way that the desired function is provided. Thus, any two components combined to perform a particular function can be seen as “associated” with each other, regardless of the architecture or intermediate components, in such a way that the desired function is provided. Similarly, any two such associated components can be seen as “operably connected” or “operably coupled” with each other to perform the desired function, and any two components having such associated functions can be seen as “operably coupled” with each other to perform the desired function. Specific examples of operably coupled components include, but are not limited to, physically matable and / or physically interacting components, wirelessly interactive and / or wirelessly interacting components, and / or logically interacting and / or logically interacting components.

[0133] The embodiments, features, systems, devices, materials, methods, and techniques described herein may, in some embodiments, be similar to one or more of the embodiments, features, systems, devices, materials, methods, and techniques described below: U.S. Patent Application No. 16 / 048,167, filed on July 27, 2017, entitled "SYSTEMS AND METHODS FOR ASSISTING AND AUGMENTING SURGICAL PROCEDURES," U.S. Patent Application No. 16 / 242,877, filed on January 8, 2019, entitled "SYSTEMS AND METHODS OF ASSISTING A SURGEON WITH SCREW PLACEMENT DURING SPINAL SURGERY". U.S. Patent Application No. 16 / 207,116, filed December 1, 2018, entitled "SYSTEMS AND METHODS FOR MULTI-PLANAR ORTHOPEDIC ALIGNMENT" U.S. Patent Application No. 16 / 352,699, filed on March 13, 2019, entitled "SYSTEMS AND METHODS FOR ORTHOPEDIC IMPLANT FIXATION," U.S. Patent Application No. 16 / 383,215, filed on April 12, 2019, entitled "SYSTEMS AND METHODS FOR ORTHOPEDIC IMPLANT FIXATION" U.S. Patent Application No. 16 / 569,494, filed on September 12, 2019, entitled "SYSTEMS AND METHODS FOR ORTHOPEDIC IMPLANTS" U.S. Patent Application No. 62 / 773,127, filed November 29, 2018, entitled "SYSTEMS AND METHODS FOR ORTHOPEDIC IMPLANTS" U.S. Patent Application No. 62 / 928,909, filed on October 31, 2019, entitled "SYSTEMS AND METHODS FOR DESIGNING ORTHOPEDIC IMPLANTS BASED ON TISSUE CHARACTERISTICS," U.S. Patent Application No. 16 / 735,222, filed on January 6, 2020, entitled "PATIENT-SPECIFIC MEDICAL PROCEDURES AND DEVICES, AND ASSOCIATED SYSTEMS AND METHODS" U.S. Patent Application No. 16 / 987,113, filed on August 6, 2020, entitled "PATIENT-SPECIFIC ARTIFICIAL DISCS, IMPLANTS AND ASSOCIATED SYSTEMS AND METHODS" U.S. Patent Application No. 16 / 990,810, filed on August 11, 2020, entitled "LINKING PATIENT-SPECIFIC MEDICAL DEVICES WITH PATIENT-SPECIFIC DATA, AND ASSOCIATED SYSTEMS, DEVICES, AND METHODS," U.S. Patent Application No. 17 / 085564, filed on October 30, 2020, entitled "SYSTEMS AND METHODS FOR DESIGNING ORTHOPEDIC IMPLANTS BASED ON TISSUE CHARACTERISTICS," and U.S. Patent Application No. 17 / 100,396, filed November 20, 2020, entitled "PATIENT-SPECIFIC VERTEBRAL IMPLANTS WITH POSITIONING FEATURES".

[0134] All of the contents of the patents and applications mentioned above are incorporated by reference. Furthermore, the embodiments, features, systems, devices, materials, methods, and techniques described herein may, in certain embodiments, be applied to or used in combination with one or more of the embodiments, features, systems, devices, or other contents.

[0135] The scope disclosed herein includes all overlaps, sub-scopes, and combinations thereof. Language such as “up to,” “at least,” “greater than,” “less than,” or “between” includes the numbers listed. Numbers following terms such as “approximately,” “about,” and “substantially” as used herein include the numbers listed (e.g., about 10% = 10%) and also represent quantities that are close to the quantity described and still perform the desired function or produce the desired result. For example, the terms “approximately,” “about,” and “substantially” may mean quantities that fall within less than 10%, less than 5%, less than 1%, less than 0.1%, and less than 0.01% of the quantity described.

[0136] From the foregoing, it will be acknowledged that various embodiments of the disclosure of the present invention have been described herein for illustrative purposes only, and that various modifications can be made without departing from the scope and spirit of the disclosure of the present invention. Accordingly, the various embodiments disclosed herein are not intended to be limiting. [Explanation of Symbols]

[0137] 500 ways to provide patient-specific medical care 502 Stage of receiving patient datasets 503 The stage of generating a virtual model of the innate anatomical structure. 504 Stage of generating a virtual model of the corrective anatomical structure 506 The stage of developing a surgical plan to achieve corrective anatomical structure.

Claims

1. A computer implementation method for providing patient-specific medical care, The stage of receiving the patient's patient dataset, A step of comparing a patient dataset with a plurality of reference patient datasets in order to identify one or more similar patient datasets within a plurality of reference patient datasets, The step of selecting one or more subsets of similar patient datasets, wherein each similar patient dataset in the selected subset includes data showing favorable treatment outcomes. A step of identifying surgical procedure data and medical device design data associated with the preferred treatment outcome for at least one similar patient dataset from the selected subsets, A step of generating at least one patient-specific surgical procedure and at least one patient-specific medical device design for the patient based on the surgical procedure data and the medical device design data, A method characterized by comprising:

2. At least one of the aforementioned similar patient datasets corresponds to (a) a reference patient having similar spinal pathology data to the patient and / or (b) a reference patient who has received treatment with the respective orthopedic implant, At least one of the similar patient datasets among the selected subsets includes data indicating that the treatment using each of the orthopedic implants accepted by the reference patient produced the favorable treatment outcome, The computer implementation method according to feature 1.

3. The computer implementation method according to claim 1, further comprising the step of generating a manufacturing order configured to cause a manufacturing system to manufacture an orthopedic implant specific to the patient in accordance with the design generated for the patient.

4. The computer implementation method according to claim 1, characterized in that each of the plurality of reference patient datasets includes data representing one or more of the following: age, sex, obesity index, lumbar lordosis, Cobb angle, pelvic incidence angle, intervertebral disc height, segmental flexibility, bone quality, rotational displacement, or spinal treatment level.

5. The aforementioned comparison stage is, For each reference patient dataset, a similarity score is generated based on a comparison between the patient dataset and the reference patient dataset. A step of identifying one or more similar patient datasets based at least partially on the similarity score, Equipped with, The computer implementation method according to feature 1.

6. The computer implementation method according to claim 4, characterized in that the similarity score represents the statistical correlation between the patient dataset and the reference patient dataset.

7. The computer implementation method according to claim 1, characterized in that the data showing the preferred treatment outcome includes data representing one or more of the following: corrective anatomical metrics, presence of melting, health-related quality of life, activity level, or complications.

8. The computer implementation method according to claim 1, characterized in that the surgical procedure data includes data representing one or more of the following: surgical technique, orthodontic operation, bone resection, or implant placement.

9. The computer implementation method according to claim 1, characterized in that the at least one medical device design includes data representing one or more of the physical, mechanical, or biological characteristics of the corresponding medical device.

10. The computer implementation method according to claim 1, characterized in that the aforementioned generation step is performed at least partially by a trained machine learning model.

11. The aforementioned trained machine learning model Based on the surgical procedure data and the medical device design data, multiple surgical procedures and corresponding medical device designs for treating the patient are determined. For each of the aforementioned multiple surgical procedures and each of the aforementioned multiple medical device designs, the probability of achieving the target treatment outcome for the patient is calculated, and Based at least in part on the calculated probability of achieving the target therapeutic outcome, at least one of the plurality of surgical procedures and at least one of the corresponding plurality of medical device designs are selected. It is configured in such a way. The computer implementation method according to feature 10.

12. The computer implementation method according to claim 1, further comprising the step of generating a manufacturing command configured to cause a manufacturing system to manufacture at least one medical device having the aforementioned at least one patient-specific medical device design.

13. The computer implementation method according to claim 1, characterized in that the design of at least one patient-specific medical device includes a design for an implant or an implant delivery device.

14. The computer implementation method according to claim 1, further comprising the step of generating control commands configured to cause a surgical robot to at least partially perform the aforementioned at least one patient-specific surgical procedure.

15. The computer implementation method according to claim 1, characterized in that the at least one patient-specific surgical procedure is a multi-site procedure for implanting a patient-specific medical device at each location along the patient's spine.

16. The step of determining the implantation site and each patient-specific medical device in order to achieve the planned outcome for the patient, which includes one or more of the following: target pelvic angle of incidence, target Cobb angle, target shoulder tilt, target iliopsoas angle, and / or coronal equilibrium. The computer implementation method according to claim 1, further comprising the following:

17. In order to generate patient-specific disease progression data, a step is taken to simulate the progression of the disease affecting the patient. Furthermore, The at least one patient-specific surgical procedure and / or the at least one patient-specific medical device design for the patient is generated based on the patient-specific disease progression data. The computer implementation method according to feature 1.

18. The computer implementation method according to claim 1, further comprising the step of comparing the disease progression data of a patient with at least one patient dataset showing similar disease progression in order to simulate the disease progression used to select the subset.

19. The patient dataset includes historical data for one or more metrics, The method is A step of predicting the change in the one or more metrics for the patient based on the historical data, A step of simulating treatment outcomes for the patient over a period of time based on the predicted changes in the one or more metrics, wherein the simulation step is performed by a machine learning model that is at least partially based on and trained on the simulation of the treatment outcomes, It also has, The computer implementation method according to feature 1.

20. A step of receiving one or more target outcome spinal parameters used to generate the at least one patient-specific surgical procedure and / or at least one patient-specific medical device design for the patient, The computer implementation method according to claim 1, further comprising the following:

21. The step of generating at least one patient-specific surgical procedure includes the step of generating multiple patient-specific surgical procedures. The method is The stage of receiving a selection from the doctor for one of the patient-specific surgical procedures, A step of manufacturing the at least one patient-specific medical device corresponding to the selected patient-specific surgical procedure, It also has, The computer implementation method according to feature 1.

22. When executed by a computer system, the computer system The stage of receiving the patient's patient dataset, A step of comparing the patient dataset with the multiple past patient datasets in order to identify one or more similar patient datasets within the multiple past patient datasets, The step of selecting one or more subsets of similar patient datasets, wherein each similar patient dataset in the selected subset is associated with a desired treatment outcome. For each similar patient dataset of the selected subset, the step of determining surgical intervention data and implant design data corresponding to the desired treatment outcome, A step of generating at least one personalized surgical intervention and at least one personalized implant design for the patient based on the surgical intervention data and the implant design data, A non-temporary computer-readable storage medium that stores instructions for performing an operation that includes the following.

23. The non-temporary computer-readable storage medium according to claim 22, further comprising the step of inputting the surgical intervention data and the implant design data into a trained machine learning model.

24. The non-temporary computer-readable storage medium according to claim 23, further comprising the step of using the trained machine learning model to calculate the likelihood of achieving the desired therapeutic outcome associated with the at least one personalized surgical intervention and the at least one personalized implant design.

25. The non-temporary computer-readable storage medium according to claim 22, characterized in that the operation includes the steps as in any one of claims 1 to 21.

26. A system for generating patient-specific medical plans, One or more processors, When executed by the aforementioned one or more processors, the system The stage of receiving patient data sets from patients, A step of comparing the patient dataset with multiple reference patient datasets, each of which is associated with a corresponding reference patient. A step of selecting a subset of the plurality of reference patient datasets based at least partially on the similarity to the patient dataset and the treatment outcomes of the corresponding reference patients, and A step of generating at least one surgical procedure or medical device design for treating the patient based on the selected subset, A memory that stores instructions for executing operations including, A system characterized by comprising the following features.

27. The system according to claim 26, further comprising a user device configured to display information relating to at least one surgical procedure or medical device design.

28. The system according to claim 26, characterized in that it is operably connected to one or more databases storing the reference data via a communication network.

29. The system according to claim 26, characterized in that it is operably coupled to a manufacturing system configured to manufacture a medical device having the aforementioned medical device design.

30. The manufacturing system according to claim 29, characterized in that it is configured to perform one or more of the following: additive manufacturing, 3D printing, stereolithography, digital photoprocessing, fusion deposition modeling, selective laser sintering, selective laser melting, electron beam melting, laminated object manufacturing, powder bed printing, thermoplastic printing, direct material deposition, or inkjet photoresin printing.

31. The system according to claim 29, characterized in that the operation includes the steps as in any one of claims 1 to 21.

32. A computer implementation method for designing patient-specific orthopedic implants, The step of receiving a patient dataset of the patient, including spinal pathology data for the patient, (a) comparing the patient dataset with a plurality of reference patient datasets in order to identify one or more similar patient datasets within a plurality of reference patient datasets, each corresponding to a reference patient having similar spinal pathology data and (b) having received treatment with each orthopedic implant, The step of selecting a subset of one or more similar patient datasets, wherein each similar patient dataset in the selected subset includes data indicating that the treatment using the respective orthopedic implants accepted by the reference patient resulted in a favorable treatment outcome, A step of identifying, for at least one similar patient dataset of the selected subset, design data for each orthopedic implant and surgical procedure data for the surgical procedure for implanting each orthopedic implant in the corresponding reference patient, Based on the design data and the surgical procedure data, a step is to generate a design for the patient-specific orthopedic implant and a surgical procedure for implanting the patient-specific orthopedic implant in the patient. A step of outputting a manufacturing command configured to cause an additive manufacturing system to manufacture the patient-specific orthopedic implant according to the generated design, A method characterized by comprising:

33. The computer implementation method according to claim 32, characterized in that each of the plurality of reference patient datasets includes spinal pathology data representing one or more of the following: lumbar lordosis, Cobb angle, pelvic incidence angle, intervertebral disc height, segmental flexibility, bone quality, rotational displacement, or spinal treatment level.

34. The aforementioned comparison stage is, For each reference patient dataset, a similarity score is generated based on a comparison between the spinal pathology data of the patient dataset and the spinal pathology data of the reference patient dataset. A step of identifying one or more similar patient datasets based at least partially on the similarity score, Equipped with, The computer implementation method according to feature 32.

35. The computer implementation method according to claim 34, characterized in that the similarity score represents the statistical correlation between the patient dataset and the reference patient dataset.

36. The computer implementation method according to claim 32, characterized in that the data showing the preferred treatment outcome includes data representing one or more of the following: corrective anatomical metrics, presence of melting, health-related quality of life, activity level, or complications.

37. The computer implementation method according to claim 32, characterized in that the surgical procedure data includes data representing one or more of the following: surgical technique, orthodontic operation, bone resection, or implant placement.

38. The computer implementation method according to 32, characterized in that the design for the patient-specific orthopedic implant includes data representing one or more of the physical, mechanical, or biological characteristics of the patient-specific orthopedic implant.

39. The computer implementation method according to 32, characterized in that the generation step is performed at least partially by a trained machine learning model.

40. The aforementioned trained machine learning model Based on the aforementioned surgical procedure data and design data, multiple surgical procedures and corresponding multiple orthopedic implant designs for treating the patient are determined. For each of the aforementioned multiple surgical procedures and each of the corresponding multiple orthopedic implant designs, the probability of achieving the target treatment outcome for the patient is calculated, and Based at least in part on the calculated probability of achieving the target treatment outcome, at least one of the plurality of surgical procedures and at least one of the corresponding plurality of orthopedic implant designs are selected. It is configured in such a way. The computer implementation method according to feature 39.

41. The computer implementation method according to claim 40, characterized in that the manufacturing order comprises a three-dimensional model of the design for the orthopedic implant specific to the patient.

42. The computer implementation method according to claim 40, further comprising the step of determining an implant delivery device for use in the surgical procedure for implanting the patient-specific orthopedic implant into the patient.

43. The computer implementation method according to claim 40, further comprising the step of generating control commands configured to cause a surgical robot to at least partially perform the surgical procedure for implanting the patient-specific orthopedic implant into the patient.

44. When executed by a computer system, the computer system The step of receiving a patient dataset of the patient, including spinal pathology data for the patient, (a) comparing the patient dataset with a plurality of past patient datasets in order to identify one or more similar patient datasets within a plurality of past patient datasets, each corresponding to a past patient who has similar spinal pathology data to the patient and (b) has received treatment with each orthopedic implant, The step of selecting one or more subsets of similar patient datasets, wherein each similar patient dataset in the selected subset is associated with data indicating that the treatment using each of the orthopedic implants accepted by the past patients produced a desirable treatment outcome; A step of determining, for each similar patient dataset of the selected subset, design data for each orthopedic implant and procedural data for the surgical procedure to implant each orthopedic implant in the corresponding past patient, A step of generating a design for a personalized orthopedic implant for the patient and a personalized surgical procedure for implanting the personalized orthopedic implant in the patient, based on the design data and the procedure data. The steps include: having the personalized orthopedic implant manufactured according to the design that was generated; A non-temporary computer-readable storage medium that stores instructions for performing operations, including those mentioned above.

45. The non-temporary computer-readable storage medium according to claim 44, further comprising the step of inputting the design data and the procedure data into a trained machine learning model.

46. The non-temporary computer-readable storage medium according to claim 45, further comprising the step of using the trained machine learning model to calculate the likelihood of achieving the desired treatment outcome associated with the personalized orthopedic implant.

47. A system for designing customized orthopedic implants for patients, One or more processors, When executed by the aforementioned one or more processors, the system The step of receiving a patient dataset of the patient, including spinal pathology data for the patient. A step in which the patient dataset is compared with multiple reference patient datasets, each associated with a corresponding reference patient who received treatment using each orthopedic implant, A step of selecting a subset of a plurality of reference patient datasets, at least in part, based on similarity to the patient dataset and the treatment outcomes of the corresponding reference patients, wherein the corresponding reference patient (a) had spinal pathology data similar to the patient, and (b) showed favorable treatment outcomes from the treatment using the respective orthopedic implants. The steps include generating a design for the customized orthopedic implant based on the selected subset, and A step of sending a manufacturing order to an additive manufacturing system configured to manufacture the customized orthopedic implant according to the design that has been generated, A memory that stores instructions for executing operations including, A system characterized by comprising the following features.

48. The system according to claim 47, further comprising a user device configured to display information relating to the design of the customized orthopedic implant.

49. The system according to claim 47, characterized in that it is operably connected to one or more databases storing the reference patient dataset via a communication network.

50. The system according to claim 47, further comprising the additive manufacturing system.

51. The additive manufacturing system is configured to manufacture the customized orthopedic implant using one or more of the following methods: 3D printing, stereolithography, digital photoprocessing, fusion deposition modeling, selective laser sintering, selective laser melting, electron beam melting, laminate fabrication, powder bed printing, thermoplastic printing, direct material deposition, or inkjet photoresin printing.

52. A step of generating an anatomical model of at least a part of the patient, wherein the anatomical model shows the patient's innate biological structure, The steps include generating a corrective anatomical model based on patient-specific corrections to the patient's innate biological structure, The steps include determining multiple treatment locations in accordance with the aforementioned corrective anatomical model, The steps include designing patient-specific implants for each of the treatment sites based on the patient-specific orthodontic and / or orthodontic anatomical models, A computer implementation method characterized by comprising:

53. The computer implementation method according to claim 52, characterized in that the patient-specific implant is configured to substantially fit the portion of the patient to the orthodontic anatomical model when the patient-specific implant is embedded in the plurality of treatment sites.

54. The computer implementation method according to claim 52, characterized in that the anatomical model is a virtual model of the spinal segment of the patient.

55. The computer implementation method according to claim 52, further comprising the step of comparing the anatomical model with the corrective anatomical model in order to determine the plurality of treatment locations.

56. The computer implementation method according to claim 52, further comprising the step of generating the patient-specific correction using a trained machine learning model.

57. The computer implementation method according to claim 56, characterized in that the patient-specific correction is a physician-input type adjustment to the anatomical model.

58. The computer implementation method according to claim 56, characterized in that the patient-specific correction includes one or more positional relationships between anatomical elements.

59. The aforementioned treatment sites and the implants specific to each patient are configured to achieve the planned outcome corresponding to the patient's specific orthodontic treatment. The aforementioned planned outcome includes one or more of the target coronal parameters and sagittal parameters. The computer implementation method according to feature 52.

60. The computer implementation method according to claim 52, characterized in that the treatment site and each patient-specific implant are configured to achieve a target pelvic incidence angle, target Cobb angle, target shoulder tilt, target iliopsoas angle, and / or target coronal equilibrium corresponding to the patient-specific correction.

61. The computer implementation method according to claim 52, characterized in that the patient-specific correction includes changes to one or more of the Cobb angle, lordosis angle, or intervertebral space height.

62. The stage of receiving the aforementioned patient-specific orthodontic treatment, The step of determining whether the patient-specific orthodontic treatment received satisfies at least one design criterion, If the received patient-specific correction satisfies at least one design judgment criterion, the step of generating the corrective anatomical model according to the received patient-specific correction, If the patient-specific orthodontic treatment received fails to satisfy the design criteria, (a) The step of modifying the received patient-specific correction and generating the corrective anatomical model in accordance with the modified received patient-specific correction, or (b) Sending a request for at least one new patient-specific correction for the patient-specific correction used to generate the corrective anatomical model, The computer implementation method according to claim 52, further comprising the above.

63. A computer-implemented method for treating a patient's spine, A step of predicting disease progression for a disease affecting the spine of a patient based on the patient's patient dataset and at least one reference patient dataset, The steps include generating a corrective anatomical model of the patient to compensate for the expected disease progression in order to achieve the target treatment outcome, The steps include designing at least one patient-specific implant based on the aforementioned orthodontic anatomical model, A method characterized by comprising:

64. A step of simulating the predicted disease progression for observation by a physician, The step of receiving physician input for the aforementioned simulation, A step of simulating at least one treatment outcome for the patient based on the received physician input and the predicted disease progression, The computer implementation method according to 63, further comprising the above.

65. A step of comparing the first image data of the patient with the second image data of the patient. Furthermore, The aforementioned predicted disease progression is based on the aforementioned comparison. The computer implementation method according to feature 63.

66. The computer implementation method according to claim 63, characterized in that the target treatment result includes a range of acceptable spinal parameters over a certain period of time.

67. The computer implementation method according to claim 63, characterized in that the at least one patient-specific implant is designed to achieve the target treatment outcome over the expected service life of the at least one patient-specific implant.

68. The step of selecting at least one suitable past patient from the one or more similar past patients mentioned above, The steps include obtaining disease progression data from at least one matching past patient, Based on the disease progression data obtained, the step of determining a patient-specific surgical intervention plan to compensate for the disease progression, The computer implementation method according to 63, further comprising the above.

69. Stages that generate multiple disease progression scenarios, The step of displaying the aforementioned disease progression scenario, A step of receiving a selection of one or more disease progression scenarios for generating the corrective anatomical model, The computer implementation method according to 63, further comprising the above.

70. The aforementioned disease progression scenario is, The rate of progression of the aforementioned disease, Patient health score, and / or Treatment period, It is caused by one or more of the following: The computer implementation method according to feature 69.

71. The computer implementation method according to claim 70, characterized in that the rate of progression is determined based on one reference patient data.

72. The computer implementation method according to claim 70, characterized in that the patient health score is determined based on the expected activity level for the patient, the patient's second disease, and / or the patient's medical condition.

73. The computer implementation method according to 69, characterized in that each of the disease progression scenarios represents the rate of disease progression.

74. A computer implementation method for providing patient-specific medical care, The steps include receiving a patient dataset for the patient, which includes one or more images of the patient's spinal region showing the patient's inherent anatomical structure, The stage of determining a corrected anatomical structure that differs from the aforementioned innate anatomical structure, The steps include generating a virtual model of the corrective anatomical structure, The steps include: generating a surgical plan to achieve the aforementioned corrective anatomical structure; The steps include designing one or more patient-specific implants to achieve the aforementioned orthodontic anatomical configuration, A method characterized by comprising:

75. The computer implementation method according to 74, further comprising the step of transmitting the virtual model of the surgical plan and / or the orthodontic anatomical configuration for surgical examination before designing the one or more patient-specific implants.

76. A step of receiving surgeon feedback regarding the surgical plan and / or the virtual model, A step of correcting the surgical plan and / or the virtual model based on the surgeon's feedback, The step of transmitting the corrected surgical plan and / or virtual model for surgical review, The computer implementation method according to claim 75, further comprising the above.

77. The computer implementation method according to 74, characterized in that the step of determining the corrective anatomical structure includes the step of analyzing one or more reference patient datasets.

78. The computer implementation method according to claim 74, characterized in that the step of determining the corrective anatomical configuration includes a step of automatically determining the corrective anatomical configuration.

79. The computer implementation method according to 74, characterized in that the step of determining the corrective anatomical configuration is performed at least partially by a trained machine learning model.

80. The computer implementation method according to claim 74, characterized in that the step of determining the corrective anatomical configuration includes the step of adjusting one or more spinal metrics associated with the spinal region of the patient.

81. The computer implementation method according to claim 80, characterized in that the one or more spinal metrics include lumbar lordosis, Cobb angle, one or more coronal parameters, one or more sagittal parameters, and / or one or more pelvic parameters.

82. The aforementioned virtual model is a second virtual model, The method further comprises the step of generating a first virtual model of the patient's innate anatomical structure. The computer implementation method according to feature 74.

83. The computer implementation method according to 82, further comprising the step of determining one or more spinal metrics of the patient, including lumbar lordosis, Cobb angle, one or more coronal parameters, one or more sagittal parameters, and / or one or more pelvic parameters, based on the first virtual model.

84. The step of generating the surgical plan includes identifying one or more target regions in the patient's spinal region for receiving the implant, The step of designing one or more patient-specific implants includes the step of designing a patient-specific implant for each of the one or more target regions. The computer implementation method according to feature 74.

85. The computer-aided implementation method according to 84, characterized in that each patient-specific implant is designed to interlock with one or more biological structures in the corresponding target region.

86. The one or more patient-specific implants include at least one first patient-specific implant configured to be embedded at a first vertebral level, and a second patient-specific implant configured to be embedded at a second vertebral level. The first patient-specific implant has a different shape from the second patient-specific implant. The computer implementation method according to feature 85.

87. The computer implementation method according to claim 74, further comprising the step of generating machine-readable manufacturing instructions for manufacturing one or more patient-specific implants.

88. The computer implementation method according to 87, further comprising the step of transmitting the machine-readable manufacturing instructions to a manufacturing system for execution.

89. The computer implementation method according to 74, characterized in that the surgical plan includes one or more surgical procedures to be performed on the patient.

90. The computer implementation method according to 89, characterized in that the one or more surgical procedures include posterior lumbar interbody fusion (PLIF), anterior lumbar interbody fusion (ALIF), transverse or transforaminal lumbar interbody fusion (TLIF), lateral lumbar interbody fusion (LLIF), true lateral lumbar interbody fusion (DLIF), and / or true transverse lumbar interbody fusion (XLIF).

91. The surgical plan includes one or more target regions of the patient's biological structure for performing the surgical procedure. The one or more target regions include one or more specific vertebral levels. The computer implementation method according to feature 89.

92. The surgical plan includes one or more spinal metrics associated with the corrective anatomical configuration. The one or more spinal metrics include lumbar lordosis, Cobb angle, one or more coronal parameters, one or more sagittal parameters, and / or one or more pelvic parameters. The computer implementation method according to feature 74.

93. A system for providing patient-specific medical care, One or more processors, When executed by the aforementioned one or more processors, the system The step of receiving a patient dataset for the patient, which includes one or more images of the patient's spinal region showing the patient's inherent anatomical structure. The stage of determining a corrective anatomical structure that differs from the aforementioned innate anatomical structure, The step of generating a virtual model of the corrective anatomical structure, The steps of generating a surgical plan to achieve the aforementioned corrective anatomical structure, and The step of designing one or more patient-specific implants to achieve the aforementioned orthodontic anatomical configuration, A memory that stores instructions for executing operations including, A system characterized by comprising the following features.

94. The system according to 93, wherein the operation further comprises the step of transmitting the virtual model of the surgical plan and / or the orthodontic anatomical configuration for surgical examination before designing the one or more patient-specific implants.

95. The aforementioned operation is, A step of receiving surgeon feedback regarding the surgical plan and / or the virtual model, A step of correcting the surgical plan and / or the virtual model based on the surgeon's feedback, The step of transmitting the corrected surgical plan and / or virtual model for surgical review, It also has, The system according to feature 94.

96. The system according to 93, characterized in that the step of determining the corrective anatomical configuration includes the step of analyzing one or more reference patient datasets.

97. The system according to claim 93, characterized in that the step of determining the corrective anatomical configuration includes a step of automatically determining the corrective anatomical configuration.

98. The system according to 93, characterized in that the step of determining the corrective anatomical configuration is performed at least in part by a trained machine learning model.

99. The system according to 93, characterized in that the step of determining the corrective anatomical configuration includes the step of adjusting one or more spinal metrics associated with the spinal region of the patient.

100. The system according to claim 99, characterized in that the one or more spinal metrics include lumbar lordosis, Cobb angle, one or more coronal parameters, one or more sagittal parameters, and / or one or more pelvic parameters.

101. The aforementioned virtual model is a second virtual model, The operation further comprises the step of generating a first virtual model of the patient's innate anatomical structure. The system according to feature 93.

102. The operation further comprises the step of determining one or more spinal metrics of the patient based on the first virtual model, The one or more spinal metrics include lumbar lordosis, Cobb angle, one or more coronal parameters, one or more sagittal parameters, and / or one or more pelvic parameters. The system according to feature 101.

103. The step of generating the surgical plan includes identifying one or more target regions in the patient's spinal region for receiving the implant, The step of designing one or more patient-specific implants includes the step of designing a patient-specific implant for each of the one or more target regions. The system according to feature 93.

104. The system according to claim 103, characterized in that each patient-specific implant is designed to interlock with one or more biological structures in the corresponding target region.

105. The one or more patient-specific implants include at least one first patient-specific implant configured to be embedded at a first vertebral level, and a second patient-specific implant configured to be embedded at a second vertebral level. The first patient-specific implant has a different shape from the second patient-specific implant. The system according to feature 104.

106. The system according to 93, wherein the operation further comprises the step of generating computer-readable manufacturing instructions for manufacturing the one or more patient-specific implants.

107. The system according to 106, wherein the operation further comprises the step of transmitting the computer-readable manufacturing instruction to the manufacturing system for execution.

108. The system according to 93, characterized in that the surgical plan includes one or more surgical procedures to be performed on the patient.

109. The system according to claim 108, characterized in that the one or more surgical procedures include posterior lumbar interbody fusion (PLIF), anterior lumbar interbody fusion (ALIF), transverse or transforaminal lumbar interbody fusion (TLIF), lateral lumbar interbody fusion (LLIF), true lateral lumbar interbody fusion (DLIF), and / or true transverse lumbar interbody fusion (XLIF).

110. The surgical plan includes one or more target regions of the patient's biological structure for performing the surgical procedure. The one or more target regions include one or more specific vertebral levels. The system according to feature 108.

111. The surgical plan includes one or more spinal metrics associated with the corrective anatomical configuration. The one or more spinal metrics include lumbar lordosis, Cobb angle, one or more coronal parameters, one or more sagittal parameters, and / or one or more pelvic parameters. The system according to feature 93.

Images