DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Applicant’s Amendments filed on December 1, 2025, has been entered and made of record.
Currently pending Claim(s) 1-20
Independent Claim(s) 1,9, and 17
Amended Claim(s) 1,9, and 16-20
Response to Arguments
This office action is responsive to Applicant’s Arguments/Remarks Made in an Amendment received on December 1, 2025.
In view of amendments filed on December 1, 2025, to the claims, the Applicant has amended claims 1-2, 9, and 17 to further define the claimed invention and distinguish it from the prior art of record, Poltaretskyi (US 2019/0380792 A1). The independent claims now include additional details about the machine learning model, the training inputs, the data captured for developing insights, and the planning of future cases. Dependent claim 2 now includes details about the intraoperative metrics captured.
The Applicant argued (Remarks pp. 8-9) that Poltaretskyi may incorporate elements of machine learning for segmentation or anatomical mapping but does not describe retraining or updating the model based on surgical outcomes. However, the Examiner respectfully disagrees. Poltaretskyi teaches recording postoperative health outcomes such as post operative pain [0853], postoperative range of motion [0853], and postoperative infections [0853], and training the neural networks using supervised learning [0855, 0892]. Poltaretskyi teaches weighting the training sets based on the operative outcomes [0850] or weighting sets based on a specific doctor’s cases, which would update the neural network parameters through additional training.
Next, the Applicant argued (Remarks pp. 9) that Poltaretskyi does not teach every limitation of the newly amended independent claims. Specifically, the Applicant argues that Poltaretskyi fails to teach training the neural network using implant sizes, orientations, and post-operative alignment scores. Regarding implant sizes and orientations, the Examiner respectfully disagrees. Poltaretskyi teaches generating operative plans including the implant size and orientation using the AI surgical planning system, which would require training on implant sizes and orientations, but the Examiner agrees that Poltareskyi fails to teach training on post-operative alignment scores. However, the use of post-operative alignment scores is known in the art as taught by Daley in at least 0019. Poltareskyi and Daley are analogous in the art, and Daley teaches recording and using post-operative alignment scores for informing machine learning methods to optimize new surgical plans for similar patients; see the rejection to claim 1 in the body of rejection below.
Next, the Applicant argued (Remarks pp. 9) that Poltareskyi does not teach using all the metrics present in the amended claim 2 for updating the parameters of the AI model in a closed-loop feedback system. However, Poltaretskyi teaches recording postoperative health outcomes [0853], and training the neural networks using supervised learning [0855, 0892] using these metrics. Poltaretskyi teaches weighting the training sets based on the operative outcomes [0850] or weighting sets based on a specific doctor’s cases, which would update the neural network parameters through additional training. Additionally, Daley teaches utilizing feedback loops of intraoperative and postoperative data for creating closed feedback loops for optimizing surgical plans for future similar patients and informing the machine learning models which generate the plans.
The Examiner acknowledges that blood loss is not recorded by Poltaretskyi. However, Nawana teaches recording operative metrics and using them to inform future surgical plans, and the operative metrics include blood loss [Col. 44, lines 42-50]. Since, Poltaretskyi and Nawana are analogous in the art, the Examiner argues that modifying Poltaretskyi’s invention to include recording blood loss would be obvious; see the rejection to claim 2 below.
Therefore, for the reasons stated above, the Examiner presents new rejections to claims 1-20 in the body of rejection below. Additionally, the Examiner had overlooked in the previous actions that the Abstract of the disclosure exceeds 150 words. The appropriate objection is made below.
Specification
Applicant is reminded of the proper content of an abstract of the disclosure.
Extensive mechanical and design details of an apparatus should not be included in the abstract. The abstract should be in narrative form and generally limited to a single paragraph within the range of 50 to 150 words in length. See MPEP § 608.01(b) for guidelines for the preparation of patent abstracts.
The abstract of the disclosure is objected to because it exceeds 150 words in length. A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b).
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on December 12, 2025 has been entered.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 and 3-20 are rejected under 35 U.S.C. 103 as being unpatentable over Poltaretskyi (US 2019/0380792 A1), in view of Daley et al. (US 2022/0084652 A1), hereafter Daley.
Regarding claim 1, Poltaretskyi teaches a computerized surgical planning process (Paragraph 0173 “Users of orthopedic surgical system 100 may use virtual planning system 102 to plan orthopedic surgeries.” Paragraph 0178 “orthopedic surgical system 200 includes a preoperative surgical planning system 202,”),
stored in memory that when executed by a process (Paragraph 0182 “the functionalities of a virtual surgical planning application, such as the BLUEPRINT™ system, can also be stored and executed by processing device(s) 210 in conjunction with memory storage device(s) (M) 215), perform steps comprising:
receiving, via input from a user on an electronic device, patient data (Paragraph 0181 “processing device(s) 210 can provide a user interface to display data and receive input from users at healthcare facility 204.” The system includes user interfaces for receiving data. Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
storing the data in a data storage (Paragraph 0182 “the functionalities of a virtual surgical planning application, such as the BLUEPRINT™ system, can also be stored and executed by processing device(s) 210 in conjunction with memory storage device(s) (M) 215.” Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans”.);
generating an operative plan for a surgical procedure by executing an artificial intelligence model using the data as input to the artificial intelligence model (Paragraph 0195 “During the automatic processing step, virtual planning system 102 (FIG. 1) may automatically develop a preliminary surgical plan for the patient. In some examples of this disclosure, virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.” Additionally, Paragraph 0899 discusses a specific example using patient data as an input vector to a neural network, which generates an output vector used by the computing system for determining the recommended type of shoulder surgery for the patient.),
wherein the artificial intelligence model is executed by an application stored on the electronic device or on a server communicatively coupled to the electronic device over a network (Fig. 2 shows the systems all connected to the network. Paragraph 0174 “For example, virtual planning system 102 may include a MR visualization device and one or more server devices, planning support system 104 may include one or more personal computers and one or more server devices, and so on.”), and
wherein the artificial intelligence model comprises a deep neural (In Fig. 123, Poltaretski shows an example of a deep neural network which is involved in the artificial intelligence system. Fig. 124 shows an example where the DNN classified shoulder pathology. Fig. 126 shows an example of using a DNN for recommending a specific type of should surgery for a patient based on past cases. The artificial intelligence model uses decisions output from the DNNs when generating a preoperative plan. See paragraphs 0865-0866.) network trained using supervised learning ([0855] “For instance, as part of training the NN, computing system 12202 may apply a cost function to determine cost values based on differences between the output vector generated by the NN and the target output vector. Computing system 12202 may then use the cost values in a backpropagation algorithm to update the weights of neurons in the NN.”),
capturing data resulting from a surgical procedure comprising at least one of intraoperative metrics, surgeon feedback, surgical outcome metrics, or post-operative clinical outcomes intraoperative or post-operative patient-specific data and surgical outcome metrics (Paragraph 0170 “systems and methods are also described herein that can be incorporated into an intelligent surgical planning system, such as artificial intelligence systems to assist with planning, implants with embedded sensors (e.g., smart implants) to provide postoperative feedback for use by the healthcare provider and the artificial intelligence system, and mobile applications to monitor and provide information to the patient and the healthcare provider in real-time or near real-time.” Paragraph 0912 “the implant can include various sensors to provide information after the surgery, as well as transceivers (e.g., RF transceivers) that facilitate collection of the data gathered by the sensors. Such data can be used to, for example, monitor the patient's recovery and assist with the patient's recovery (e.g., by prompting the patient to move the joint, such as via an application installed on a mobile device used by the patient, as one example).”);
storing the data in the data storage (Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans.” Paragraph 0912 “The data gathered by the sensors also can be input into a database where it can be used by surgeons or artificial intelligence systems to assist with planning future surgical cases.”);
developing insights for the artificial intelligence model based on the stored data (Paragraph 0912 “The data gathered by the sensors also can be input into a database where it can be used by surgeons or artificial intelligence systems to assist with planning future surgical cases.” Additionally, the MR system provides the ability for revising and updating surgical plans developed by the AI system—see paragraph 0184.); and
updating parameters of the artificial intelligence model based on the insights (Paragraph 0855 teaches methods of updating neural networks with new training data. Paragraph 0846 “For instance, a healthcare professional may prefer to use a NN that has been trained such that confidence levels are weighted in particular ways. In some examples where training datasets include training datasets based on a healthcare professional's own cases, the healthcare professional (e.g., an orthopedic surgeon) may prefer to use a NN trained using training datasets where the healthcare professional's own cases are weighted more heavily or exclusively using the healthcare professional's own cases. In this way, the NN may generate output tailored to the healthcare professional's own style of practice.” Paragraph 0850 “In some examples, the training datasets are weighted based on health outcomes of the training data patients. For example, a training dataset may be given higher weight if the training data patient associated with the training dataset had all positive health outcomes. However, a training dataset may be given a lower weight if the associated training data patient had less positive health outcomes. During training, computing system 12202 may use a loss function that weights the training datasets based on the weights given to the training datasets.” Additionally, Paragraph 0196 mentions that doctors may record instances where they disagree with surgery plans generated by the machine learning techniques, and these instances can be implemented as training data to refine the machine learning technique.),
wherein the insights are values for updating the parameters of the artificial intelligence model (Paragraph 0850 “In some examples, the training datasets are weighted based on health outcomes of the training data patients. For example, a training dataset may be given higher weight if the training data patient associated with the training dataset had all positive health outcomes. However, a training dataset may be given a lower weight if the associated training data patient had less positive health outcomes. During training, computing system 12202 may use a loss function that weights the training datasets based on the weights given to the training datasets.”), and
Poltaretskyi teaches utilizing patient specific inputs to the DNN(s) such as patent morphological inputs [0867], demographic information [0890], BMI [0890], and postoperative health outcomes such as post operative pain [0853], postoperative range of motion [0853], and postoperative infections [0853]. Additionally, Poltaretskyi teaches that surgical plans involve determining implant size and orientation [0221, 0233] and that the artificial intelligence system can determine the type of surgery to perform and the type of implant [0173]. Thus, training the AI models would involve training with implant types and orientations. However, Poltaretskyi fails to teach specifically using post-operative alignment scores for training DNNs.
However, Daley teaches where the model is trained on a dataset comprising at least implant sizes, implant orientations, and post-operative alignment scores (See Fig. 3. Daley teaches using AI techniques for determining and optimizing preoperative surgical plans, storing data intraoperative and postoperative data from the plan, and using feedback loops to analyze outcomes and determine better plans for similar patients. The outcomes include a KSS score, which includes post-operative alignment scores. [0019] “The information regarding the results of a surgical procedure from a patient may include electronic medical records (EMR) data, data related to the knee society clinical rating system (KSS).” Like in Poltareskyi, Daley also teaches that preoperative plans include implant type and orientation [0003, 0009, 0021-0022].).
Poltaretskyi and Daley are analogous in the art to the claimed invention because both teach utilizing AI and machine learning methods for analyzing and/or generating operative plans related to surgical implants and using feedback loops to update models based on patient outcomes for treating similar future patients. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Poltareskyi’s invention to include a KSS in the datasets used for training DNNs. This modification would include involve recording alignment outcomes, which is necessary since preoperative plans are based on alignment data ([Daley 0009] “In some examples, the system or method may generate suggested prosthetic positioning data, bone preparation data such as positioned where the surgeon should cut the bone, and/or an operative plan based… (8) lower extremity mechanical alignment, (9) lower extremity anatomical alignment, (10) femoral articular surface angle, (11) tibial articular surface angle, (12) mechanical axis alignment strategy, (13) anatomical alignment strategy, (14) natural knee alignment strategy.”). Additionally, Poltaretskyi teaches postoperative monitoring of at least symptoms, range of motion, complications, and performance of implants [0201], and postoperative measurements are stored in a database [0233].
Additionally, although Poltaretskyi teaches training models for assisting in diagnosing future cases of other patients, Poltaretskyi doesn’t specifically mention that revised operative plans are generated for future surgical procedures of a different patient based on accumulated surgical data and outcomes from prior patients having similar clinical parameters.
However, Daley teaches wherein the updated artificial intelligence model is deployed by the application to generate revised operative plans for future surgical procedures of a different patient based on accumulated surgical data and outcomes from prior patients having similar clinical parameters (See Fig. 3 Steps 301, 401, 500, and 501. Daley teaches utilizing machine learning for analyzing a preoperative plan and its outcomes to generate an optimized plan for use with future patients with similar parameters. [0013] “The system and method of various embodiments of the present disclosure includes providing this received information on changes to the initial preoperative plan and physical or virtual model in a first automated electronically transmitted feedback loop (that may employ the use of any type of conventional server, physical flash drives, Internet wired or wireless data transfer, data transfer through physical server, data transfer through cloud-based servers, and/or otherwise electronically or digitally based systems) to enable the system and method to automatically and/or manually create or design more accurate or enhanced future initial preoperative plans and enhanced physical or virtual models for subsequent patients who share specific common features tracked by the system and method.” [0016] “The system and method of various embodiments of the present disclosure includes providing this further received patient result information in a third automated electronic feedback loop… to enable the system and method to automatically and/or manually create or design more accurate or enhanced future initial preoperative plans and enhanced physical or virtual models for subsequent patients who share specific common features tracked by the system and method.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Poltareskyi’s invention by revising operative plans for subsequent patients who share similar clinical parameters. This modification would further enhance Poltareskyi’s methods by helping in designing more accurate future plans ([0046] “As indicated by block 240, the information is provided back to the system for the plurality of preoperative plans through the feedback loop to create or design more accurate future preoperative plans.”).
Regarding claim 3, Poltaretskyi teaches the computerized surgical planning process of claim 1, wherein at least one of the server or the electronic device includes the data storage (Fig. 2; Paragraph 0187 “the surgical planning system includes a storage system 206 to store data corresponding to the virtual surgical plan.” Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans... Storage system 206 can be a cloud-based storage system (as shown) or can be located at healthcare facility 204 or at the location of preoperative surgical planning system 202 or can be part of MR system 212 or visualization device (VD) 213”); and
wherein the executing the artificial intelligence model occurs via at least one of the server or the electronic device (Fig. 125; Paragraph 0119 “FIG. 125 is a block diagram illustrating example functional components of a computing system for using a DNN to determine a recommended surgery for a shoulder condition, in accordance with a technique of this disclosure.”).
Regarding claim 4, Poltaretskyi teaches the computerized surgical planning process of claim 1, wherein the surgical procedure includes cutting tissue for receiving at least one of an implant or a prosthesis (Paragraph 0353 “orthopedic surgical procedures may involve performing various work on a patient's anatomy. Some examples of work that may be performed include, but are not necessarily limited to, cutting, drilling, reaming, screwing, adhering, and impacting.” Paragraph 0481 “In operation, MR system 212 may obtain, from a virtual surgical plan, a target value of a parameter of a modification to be made to a portion of a patient's anatomy with a tool (7200). Examples of parameters include, locations at which holes are to be drilled, depths (e.g., drilling depths, reaming depths, etc.), locations of cutting surfaces, etc.” In this instance, the virtual surgical plan can be a preoperative plan generated by artificial intelligence.).
Regarding claim 5, Poltaretskyi teaches the computerized surgical planning process of claim 4, wherein the data corresponds to at least one of position, orientation, or size of at least one of the implant of the surgical procedure, the prosthesis of the surgical procedure, or a cut of the surgical procedure, and wherein user input is not required when the data includes an image (Fig. 42A-C; Paragraph 0391 “As such, MR system 212 may display a virtual cutting surface (e.g., cutting plane) having parameters (e.g., position, size, and/or orientation relative to the virtual model of the humerus) obtained from the virtual surgical plan that guides resection of a portion of a head of the humerus.” In this instance, the virtual surgical plan can be a preoperative plan generated by artificial intelligence, and the data generated by the surgical plan corresponds to the position, orientation, and size of a cut.).
Regarding claim 6, Poltaretskyi teaches the computerized surgical planning process of claim 5, wherein at least one of the server or the electronic device includes the data storage (Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans... Storage system 206 also can include data identifying the implant components selected for a particular patient (e.g., type, size, etc.), surgical guides selected for a particular patient, and details of the surgical procedure, such as entry points, cutting planes, drilling axes, reaming depths, etc. Storage system 206 can be a cloud-based storage system (as shown) or can be located at healthcare facility 204 or at the location of preoperative surgical planning system 202 or can be part of MR system 212 or visualization device (VD) 213”); and
wherein the executing the artificial intelligence model occurs via at least one of the server or the electronic device (Fig. 125; Paragraph 0119 “FIG. 125 is a block diagram illustrating example functional components of a computing system for using a DNN to determine a recommended surgery for a shoulder condition, in accordance with a technique of this disclosure.”)
Regarding claim 7, Poltaretskyi teaches the computerized surgical planning process of claim 6, wherein the data comprises at least one of an image or patient information (Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
Regarding claim 8, Poltaretskyi teaches the computerized surgical planning process of claim 7, wherein the artificial intelligence model is trained to generate the operative plan at least based on training data (Paragraph 0195 “virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.”);
and wherein the operative plan comprises: a list of medical instruments for use during the surgical procedure; and/or a list of surgical steps to perform the surgical procedure (Paragraph 0162 “Use of these planning tools typically results in generation of a preoperative surgical plan, complete with an implant and surgical instruments that are selected or manufactured for the individual patient.”),
wherein each surgical step is associated with one or more of the medical instruments from the list of medical instruments (Paragraph 0221 “Examples of preoperative planning content 702 may include a surgical plan for a shoulder arthroplasty, virtual 3D model information representing scapula and/or glenoid bone, or representing humeral bone, with virtual 3D model information of instruments to be applied to the bone or implants to be positioned on or in the bone.”).
Regarding claim 9, Poltaretskyi teaches a computerized surgical planning system (Paragraph 0173 “Users of orthopedic surgical system 100 may use virtual planning system 102 to plan orthopedic surgeries.” Paragraph 0178 “orthopedic surgical system 200 includes a preoperative surgical planning system 202,”), comprising:
an electronic device with an interface configured to receive input from a user (Paragraph 0181 “processing device(s) 210 can provide a user interface to display data and receive input from users at healthcare facility 204.”)
the input including data (Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
a server that receives the data (Paragraph 0174 “The systems in the subsystems of orthopedic surgical system 100 may include various types of computing systems, computing devices, including server computers, personal computers, tablet computers, smartphones, display devices, Internet of Things (IoT) devices, visualization devices…” Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans... Storage system 206 can be a cloud-based storage system (as shown) or can be located at healthcare facility 204 or at the location of preoperative surgical planning system 202 or can be part of MR system 212 or visualization device (VD) 213”);
a data storage that stores the data; (Fig. 2; Paragraph 0187 “the surgical planning system includes a storage system 206 to store data corresponding to the virtual surgical plan.”);
a memory storing an application; a processor which executes the application (Paragraph 0182 “the functionalities of a virtual surgical planning application, such as the BLUEPRINT™ system, can also be stored and executed by processing device(s) 210 in conjunction with memory storage device(s) (M) 215”)
to cause the system to:
receive, via input from a user, data (Paragraph 0181 “processing device(s) 210 can provide a user interface to display data and receive input from users at healthcare facility 204.” The system includes user interfaces for receiving data. Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
store the data in a data storage (Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans”.);
generate an operative plan for a surgical procedure by executing an artificial intelligence model using the data as input to the artificial intelligence model (Paragraph 0195 “During the automatic processing step, virtual planning system 102 (FIG. 1) may automatically develop a preliminary surgical plan for the patient. In some examples of this disclosure, virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.” Additionally, Paragraph 0899 discusses a specific example using patient data as an input vector to a neural network, which generates an output vector used by the computing system for determining the recommended type of shoulder surgery for the patient.)
wherein the artificial intelligence model is executed by an application stored on the electronic device or on a server communicatively coupled to the electronic device over a network (Fig. 2 shows the systems all connected to the network. Paragraph 0174 “For example, virtual planning system 102 may include a MR visualization device and one or more server devices, planning support system 104 may include one or more personal computers and one or more server devices, and so on.”), and
wherein the operative plan comprises a sequence of surgical steps ([0160] “A surgical plan, e.g., as generated by the BLUEPRINT™ system or another surgical planning platform, may include information defining a variety of features of a surgical procedure, such as features of particular surgical procedure steps to be performed on a patient by a surgeon according to the surgical plan including, for example, bone or tissue preparation steps and/or steps for selection, modification and/or placement of implant components.” A surgical plan comprises a sequence of surgical steps.)
customized for the patient using the artificial intelligence model (Paragraph 0195 “During the automatic processing step, virtual planning system 102 (FIG. 1) may automatically develop a preliminary surgical plan for the patient. In some examples of this disclosure, virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.” Later paragraphs in the 0800’s—starting with 0821—describe the different NNs that make up the virtual planning system for developing a surgical plan. Paragraph 0833 “This disclosure describes to the orthopedic classification and surgery planning using artificial intelligence (AI) techniques such as neural networks.” For examples, see the neural network for classifying a shoulder injuries in paragraph 0891 and the neural network for determining the recommended type of shoulder surgery for a specific patient in paragraph 0899.)
trained with a dataset of historical patient outcomes (Paragraph 0854 “Additional training datasets may be added to the database over time and computing system 12202 may use the additional training datasets to train the NN. Thus, the NN may continue to improve over time as more training datasets are added to the database.” Many mentions of using historical patient outcomes as training data occur throughout Poltaretskyi’s disclosure; for example, paragraph 0903 mentions a database containing “training datasets from past shoulder surgery cases.”);
capture operative data resulting from a surgical procedure comprising intraoperative or post-operative patient-specific data and surgical outcome metrics (Paragraph 0170 “systems and methods are also described herein that can be incorporated into an intelligent surgical planning system, such as artificial intelligence systems to assist with planning, implants with embedded sensors (e.g., smart implants) to provide postoperative feedback for use by the healthcare provider and the artificial intelligence system, and mobile applications to monitor and provide information to the patient and the healthcare provider in real-time or near real-time.” Paragraph 0912 “the implant can include various sensors to provide information after the surgery, as well as transceivers (e.g., RF transceivers) that facilitate collection of the data gathered by the sensors. Such data can be used to, for example, monitor the patient's recovery and assist with the patient's recovery (e.g., by prompting the patient to move the joint, such as via an application installed on a mobile device used by the patient, as one example).”);
store the operative data in the data storage; develop insights for the artificial intelligence model based on the stored data (Paragraph 0912 “The data gathered by the sensors also can be input into a database where it can be used by surgeons or artificial intelligence systems to assist with planning future surgical cases.” Additionally, the MR system provides the ability for revising and updating surgical plans developed by the AI system—see paragraph 0184.); and
update parameters of the artificial intelligence model based on the insights, wherein the insights are values for updating the parameters of the artificial intelligence model (Paragraph 0846 “For instance, a healthcare professional may prefer to use a NN that has been trained such that confidence levels are weighted in particular ways. In some examples where training datasets include training datasets based on a healthcare professional's own cases, the healthcare professional (e.g., an orthopedic surgeon) may prefer to use a NN trained using training datasets where the healthcare professional's own cases are weighted more heavily or exclusively using the healthcare professional's own cases. In this way, the NN may generate output tailored to the healthcare professional's own style of practice.” Paragraph 0850 “In some examples, the training datasets are weighted based on health outcomes of the training data patients. For example, a training dataset may be given higher weight if the training data patient associated with the training dataset had all positive health outcomes. However, a training dataset may be given a lower weight if the associated training data patient had less positive health outcomes. During training, computing system 12202 may use a loss function that weights the training datasets based on the weights given to the training datasets.” Additionally, Paragraph 0196 mentions that doctors may record instances where they disagree with surgery plans generated by the machine learning technique, and these instances can be implemented as training data to refine the machine learning technique.), and
wherein the updated artificial intelligence model is deployed by the application to generate revised operative plans for future surgical procedures based on accumulated surgical data and outcomes from prior patients (Poltaretskyi teaches recording and storing accumulated surgical data for future use by the artificial intelligence surgical planning systems. Paragraph 0912 “The data gathered by the sensors also can be input into a database where it can be used by surgeons or artificial intelligence systems to assist with planning future surgical cases.” Additionally, Poltaretskyi teaches using the health outcomes from prior patients as training data. Paragraph 0850 “In some examples, the training datasets are weighted based on health outcomes of the training data patients. For example, a training dataset may be given higher weight if the training data patient associated with the training dataset had all positive health outcomes. However, a training dataset may be given a lower weight if the associated training data patient had less positive health outcomes. During training, computing system 12202 may use a loss function that weights the training datasets based on the weights given to the training datasets.” This data is used for updating and retraining the neural network models. Paragraph 0825 “…a computing system may generate a plurality of training datasets from past shoulder surgery cases. Each respective training dataset corresponds to a different training data patient in a plurality of training data patients and comprises a respective training input vector and a respective target output vector.” Paragraph 0854 “Additional training datasets may be added to the database over time and computing system 12202 may use the additional training datasets to train the NN. Thus, the NN may continue to improve over time as more training datasets are added to the database.” Furthermore, Poltaretskyi teaches that the intelligent system—which was trained on the data listed above—can include postoperative tools which plan future surgical revisions and plans for other patients. Paragraph 0169 “These mixed reality systems and methods can be part of an intelligent surgical planning system that includes multiple subsystems that can be used to enhance surgical outcomes. In addition to the preoperative and intraoperative applications discussed above, an intelligent surgical planning system can include postoperative tools to assist with patient recovery and which can provide information that can be used to assist with and plan future surgical revisions or surgical cases for other patients.”).
Regarding claim 10, Poltaretskyi teaches the computerized surgical planning system of claim 9, wherein the data comprises at least one of an image or patient information (Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
Regarding claim 11, Poltaretskyi teaches the computerized surgical planning system of claim 9, wherein at least one of the server or the electronic device includes the data storage (Fig. 2; Paragraph 0187 “the surgical planning system includes a storage system 206 to store data corresponding to the virtual surgical plan.” Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans... Storage system 206 can be a cloud-based storage system (as shown) or can be located at healthcare facility 204 or at the location of preoperative surgical planning system 202 or can be part of MR system 212 or visualization device (VD) 213”); and
wherein the executing the artificial intelligence model occurs via at least one of the server or the electronic device (Fig. 125; Paragraph 0119 “FIG. 125 is a block diagram illustrating example functional components of a computing system for using a DNN to determine a recommended surgery for a shoulder condition, in accordance with a technique of this disclosure.”).
Regarding claim 12, Poltaretskyi teaches the computerized surgical planning system of claim 9, wherein the surgical procedure includes cutting tissue for receiving at least one of an implant or a prosthesis (Paragraph 0353 “orthopedic surgical procedures may involve performing various work on a patient's anatomy. Some examples of work that may be performed include, but are not necessarily limited to, cutting, drilling, reaming, screwing, adhering, and impacting.” Paragraph 0481 “In operation, MR system 212 may obtain, from a virtual surgical plan, a target value of a parameter of a modification to be made to a portion of a patient's anatomy with a tool (7200). Examples of parameters include, locations at which holes are to be drilled, depths (e.g., drilling depths, reaming depths, etc.), locations of cutting surfaces, etc.” In this instance, the virtual surgical plan can be a preoperative plan generated by artificial intelligence.).
Regarding claim 13, Poltaretskyi teaches the computerized surgical planning system of claim 12, wherein the capturing operative data from the surgical procedure comprises: wherein the operative data corresponds to at least one of position, orientation, or size of at least one of the implant of the surgical procedure, the prosthesis of the surgical procedure, or a cut of the surgical procedure (Paragraph 0184 “MR system 212 can be used by a surgeon before (e.g., preoperatively) or during the surgical procedure (e.g., intraoperatively) to create, review, verify, update, modify and/or implement a surgical plan. In some examples, MR system 212 may also be used after the surgical procedure (e.g., postoperatively) to review the results of the surgical procedure, assess whether revisions are required, or perform other postoperative tasks. To that end, MR system 212 may include a visualization device 213 that may be worn by the surgeon and (as will be explained in further detail below) is operable to display a variety of types of information, including a 3D virtual image of the patient's diseased, damaged, or postsurgical joint and details of the surgical plan, such as a 3D virtual image of the prosthetic implant components selected for the surgical plan, 3D virtual images of entry points for positioning the prosthetic components, alignment axes and cutting planes for aligning cutting or reaming tools to shape the bone surfaces, or drilling tools to define one or more holes in the bone surfaces, in the surgical procedure to properly orient and position the prosthetic components, surgical guides and instruments and their placement on the damaged joint, and any other information that may be useful to the surgeon to implement the surgical plan.” Paragraph 0183 “Storage system 206 also can include data identifying the implant components selected for a particular patient (e.g., type, size, etc.), surgical guides selected for a particular patient, and details of the surgical procedure, such as entry points, cutting planes, drilling axes, reaming depths, etc.” Intraoperative data is captured by the MR system in addition to the operative data captured by smart implants provided as an example in the rationale of claim 1.).
Regarding claim 14, Poltaretskyi teaches the computerized surgical planning system of claim 13, wherein at least one of the server or the electronic device includes the data storage (Fig. 2; Paragraph 0187 “the surgical planning system includes a storage system 206 to store data corresponding to the virtual surgical plan.” Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans... Storage system 206 can be a cloud-based storage system (as shown) or can be located at healthcare facility 204 or at the location of preoperative surgical planning system 202 or can be part of MR system 212 or visualization device (VD) 213”); and
wherein the executing the artificial intelligence model occurs via at least one of the server or the electronic device (Fig. 125; Paragraph 0119 “FIG. 125 is a block diagram illustrating example functional components of a computing system for using a DNN to determine a recommended surgery for a shoulder condition, in accordance with a technique of this disclosure.”).
Regarding claim 15, Poltaretskyi teaches the computerized surgical planning system of claim 14, wherein the data comprises at least one of an image or patient information (Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
Regarding claim 16, Poltaretskyi teaches the computerized surgical planning system of claim 15, wherein the artificial intelligence model is trained to generate the operative plan at least based on training data (Paragraph 0195 “virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.”); and
wherein the operative plan comprises:
a list of medical instruments for use during the surgical procedure (Paragraph 0162 “Use of these planning tools typically results in generation of a preoperative surgical plan, complete with an implant and surgical instruments that are selected or manufactured for the individual patient.”);
and/or a list of surgical steps to perform the surgical procedure, wherein each surgical step is associated with one or more of the medical instruments from the list of medical instruments (Paragraph 0221 “Examples of preoperative planning content 702 may include a surgical plan for a shoulder arthroplasty, virtual 3D model information representing scapula and/or glenoid bone, or representing humeral bone, with virtual 3D model information of instruments to be applied to the bone or implants to be positioned on or in the bone.”).
Regarding claim 17, Poltaretskyi teaches a non-transitory computer readable medium having computer readable instructions executable by a processor which, when executed, performs a process for generating an operative plan for a surgical procedure (Paragraph 0182 “the functionalities of a virtual surgical planning application, such as the BLUEPRINT™ system, can also be stored and executed by processing device(s) 210 in conjunction with memory storage device(s) (M) 215” Fig.2 shows the processing devices 210 are connected to a storage system 206);
the process comprising:
receiving, via input from a user, data (Paragraph 0181 “processing device(s) 210 can provide a user interface to display data and receive input from users at healthcare facility 204.”);
storing the data in a data storage (Fig. 2; Paragraph 0187 “the surgical planning system includes a storage system 206 to store data corresponding to the virtual surgical plan.”);
generating an operative plan for a surgical procedure by executing an artificial intelligence model using the data as input to the artificial intelligence model (Paragraph 0195 “During the automatic processing step, virtual planning system 102 (FIG. 1) may automatically develop a preliminary surgical plan for the patient. In some examples of this disclosure, virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.” Additionally, Paragraph 0899 discusses a specific example using patient data as an input vector to a neural network, which generates an output vector used by the computing system for determining the recommended type of shoulder surgery for the patient.)
wherein the artificial intelligence model is executed by an application stored on the electronic device or on a server communicatively coupled to the electronic device over a network (Fig. 2 shows the systems all connected to the network. Paragraph 0174 “For example, virtual planning system 102 may include a MR visualization device and one or more server devices, planning support system 104 may include one or more personal computers and one or more server devices, and so on.”), and
wherein the artificial intelligence model comprises a deep neural network (In Fig. 123, Poltaretski shows an example of a deep neural network which is involved in the artificial intelligence system. Fig. 124 shows an example where the DNN classified shoulder pathology. Fig. 126 shows an example of using a DNN for recommending a specific type of should surgery for a patient based on past cases. The artificial intelligence model uses decisions output from the DNNs when generating a preoperative plan. See paragraphs 0865-0866.) trained using supervised learning ([0855] “For instance, as part of training the NN, computing system 12202 may apply a cost function to determine cost values based on differences between the output vector generated by the NN and the target output vector. Computing system 12202 may then use the cost values in a backpropagation algorithm to update the weights of neurons in the NN.”),
wherein the operative plan comprises a sequence of surgical steps ([0160] “A surgical plan, e.g., as generated by the BLUEPRINT™ system or another surgical planning platform, may include information defining a variety of features of a surgical procedure, such as features of particular surgical procedure steps to be performed on a patient by a surgeon according to the surgical plan including, for example, bone or tissue preparation steps and/or steps for selection, modification and/or placement of implant components.” A surgical plan comprises a sequence of surgical steps.)
customized for the patient using the artificial intelligence model (Paragraph 0195 “During the automatic processing step, virtual planning system 102 (FIG. 1) may automatically develop a preliminary surgical plan for the patient. In some examples of this disclosure, virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.” Later paragraphs in the 0800’s—starting with 0821—describe the different NNs that make up the virtual planning system for developing a surgical plan. Paragraph 0833 “This disclosure describes to the orthopedic classification and surgery planning using artificial intelligence (AI) techniques such as neural networks.” For examples, see the neural network for classifying shoulder injuries in paragraph 0891 and the neural network for determining the recommended type of shoulder surgery for a specific patient in paragraph 0899.)
trained with a dataset of historical patient outcomes (Paragraph 0854 “Additional training datasets may be added to the database over time and computing system 12202 may use the additional training datasets to train the NN. Thus, the NN may continue to improve over time as more training datasets are added to the database.” Many mentions of using historical patient outcomes as training data occur throughout Poltaretskyi’s disclosure; for example, paragraph 0903 mentions a database containing “training datasets from past shoulder surgery cases.”);
capturing operative data resulting from a surgical procedure at least one of intraoperative metrics, surgeon feedback, surgical outcome metrics, or post-operative clinical outcomes (Paragraph 0170 “systems and methods are also described herein that can be incorporated into an intelligent surgical planning system, such as artificial intelligence systems to assist with planning, implants with embedded sensors (e.g., smart implants) to provide postoperative feedback for use by the healthcare provider and the artificial intelligence system, and mobile applications to monitor and provide information to the patient and the healthcare provider in real-time or near real-time.” Paragraph 0912 “the implant can include various sensors to provide information after the surgery, as well as transceivers (e.g., RF transceivers) that facilitate collection of the data gathered by the sensors. Such data can be used to, for example, monitor the patient's recovery and assist with the patient's recovery (e.g., by prompting the patient to move the joint, such as via an application installed on a mobile device used by the patient, as one example).”);
storing the operative data in the data storage; developing insights for the artificial intelligence model based on the stored data (Paragraph 0912 “The data gathered by the sensors also can be input into a database where it can be used by surgeons or artificial intelligence systems to assist with planning future surgical cases.”); and
updating parameters of the artificial intelligence model based on the insights, wherein the insights are values for updating the parameters of the artificial intelligence model (Paragraph 0846 “For instance, a healthcare professional may prefer to use a NN that has been trained such that confidence levels are weighted in particular ways. In some examples where training datasets include training datasets based on a healthcare professional's own cases, the healthcare professional (e.g., an orthopedic surgeon) may prefer to use a NN trained using training datasets where the healthcare professional's own cases are weighted more heavily or exclusively using the healthcare professional's own cases. In this way, the NN may generate output tailored to the healthcare professional's own style of practice.” Paragraph 0850 “In some examples, the training datasets are weighted based on health outcomes of the training data patients. For example, a training dataset may be given higher weight if the training data patient associated with the training dataset had all positive health outcomes. However, a training dataset may be given a lower weight if the associated training data patient had less positive health outcomes. During training, computing system 12202 may use a loss function that weights the training datasets based on the weights given to the training datasets.” Additionally, Paragraph 0196 mentions that doctors may record instances where they disagree with surgery plans generated by the machine learning technique, and these instances can be implemented as training data to refine the machine learning technique.).
Poltaretskyi teaches utilizing patient specific inputs to the DNN(s) such as patent morphological inputs [0867], demographic information [0890], BMI [0890], and postoperative health outcomes such as post operative pain [0853], postoperative range of motion [0853], and postoperative infections [0853]. Additionally, Poltaretskyi teaches that surgical plans involve determining implant size and orientation [0221, 0233] and that the artificial intelligence system can determine the type of surgery to perform and the type of implant [0173]. Thus, training the AI models would involve training with implant types and orientations. However, Poltaretskyi fails to teach specifically using post-operative alignment scores for training DNNs.
However, Daley teaches where the model is trained on a dataset comprising at least implant sizes, implant orientations, and post-operative alignment scores (See Fig. 3. Daley teaches using AI techniques for determining and optimizing preoperative surgical plans, storing data intraoperative and postoperative data from the plan, and using feedback loops to analyze outcomes and determine better plans for similar patients. The outcomes include a KSS score, which includes post-operative alignment scores. [0019] “The information regarding the results of a surgical procedure from a patient may include electronic medical records (EMR) data, data related to the knee society clinical rating system (KSS).” Like in Poltareskyi, Daley also teaches that preoperative plans include implant type and orientation [0003, 0009, 0021-0022].).
Poltaretskyi and Daley are analogous in the art to the claimed invention because both teach utilizing AI and machine learning methods for analyzing and/or generating operative plans related to surgical implants and using feedback loops to update models based on patient outcomes for treating similar future patients. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Poltareskyi’s invention to include a KSS in the datasets used for training DNNs. This modification would include involve recording alignment outcomes, which is necessary since preoperative plans are based on alignment data ([Daley 0009] “In some examples, the system or method may generate suggested prosthetic positioning data, bone preparation data such as positioned where the surgeon should cut the bone, and/or an operative plan based… (8) lower extremity mechanical alignment, (9) lower extremity anatomical alignment, (10) femoral articular surface angle, (11) tibial articular surface angle, (12) mechanical axis alignment strategy, (13) anatomical alignment strategy, (14) natural knee alignment strategy.”). Additionally, Poltaretskyi teaches postoperative monitoring of at least symptoms, range of motion, complications, and performance of implants [0201], and postoperative measurements are stored in a database [0233].
Additionally, although Poltaretskyi teaches training models for assisting in diagnosing future cases of other patients, Poltaretskyi doesn’t specifically mention that revised operative plans are generated for future surgical procedures of a different patient based on accumulated surgical data and outcomes from prior patients having similar clinical parameters.
However, Daley teaches wherein the updated artificial intelligence model is deployed by the application to generate revised operative plans for future surgical procedures of a different patient based on accumulated surgical data and outcomes from prior patients having similar clinical parameters (See Fig. 3 Steps 301, 401, 500, and 501. Daley teaches utilizing machine learning for analyzing a preoperative plan and its outcomes to generate an optimized plan for use with future patients with similar parameters. [0013] “The system and method of various embodiments of the present disclosure includes providing this received information on changes to the initial preoperative plan and physical or virtual model in a first automated electronically transmitted feedback loop (that may employ the use of any type of conventional server, physical flash drives, Internet wired or wireless data transfer, data transfer through physical server, data transfer through cloud-based servers, and/or otherwise electronically or digitally based systems) to enable the system and method to automatically and/or manually create or design more accurate or enhanced future initial preoperative plans and enhanced physical or virtual models for subsequent patients who share specific common features tracked by the system and method.” [0016] “The system and method of various embodiments of the present disclosure includes providing this further received patient result information in a third automated electronic feedback loop… to enable the system and method to automatically and/or manually create or design more accurate or enhanced future initial preoperative plans and enhanced physical or virtual models for subsequent patients who share specific common features tracked by the system and method.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Poltareskyi’s invention by revising operative plans for subsequent patients who share similar clinical parameters. This modification would further enhance Poltareskyi’s methods by helping in designing more accurate future plans ([0046] “As indicated by block 240, the information is provided back to the system for the plurality of preoperative plans through the feedback loop to create or design more accurate future preoperative plans.”).
Regarding claim 18, Poltaretskyi teaches the non-transitory computer readable medium of claim 17, wherein the data comprises at least one of an image or patient information (Paragraph 0192 “During the case creation step, the medical professional or other user establishes an electronic case file for the patient. The electronic case file for the patient may include information related to the patient, such as data regarding the patient's symptoms, patient range of motion observations, data regarding a surgical plan for the patient, medical images of the patients, notes regarding the patient, billing information regarding the patient, and so on.” Additionally, paragraph 0194 discusses the process of the medical image acquisition step for completing MRI, ultrasound, etc. to collect patient data.);
wherein at least one of the server or the electronic device includes the data storage (Fig. 2; Paragraph 0187 “the surgical planning system includes a storage system 206 to store data corresponding to the virtual surgical plan.” Paragraph 0183 “Storage system 206 can include one or more databases that can contain patient information, medical information, patient image data, and parameters that define the surgical plans... Storage system 206 can be a cloud-based storage system (as shown) or can be located at healthcare facility 204 or at the location of preoperative surgical planning system 202 or can be part of MR system 212 or visualization device (VD) 213”); and
wherein the executing the artificial intelligence model occurs via at least one of the server or the electronic device (Fig. 125; Paragraph 0119 “FIG. 125 is a block diagram illustrating example functional components of a computing system for using a DNN to determine a recommended surgery for a shoulder condition, in accordance with a technique of this disclosure.”).
Regarding claim 19, Poltaretskyi teaches the non-transitory computer readable medium of claim 18, wherein the surgical procedure includes cutting tissue for receiving at least one of an implant or a prosthesis; and wherein the data corresponds to at least one of position, orientation, or size of at least one of the implant of the surgical procedure, the prosthesis of the surgical procedure, or a cut of the surgical procedure (Paragraph 0184 “MR system 212 can be used by a surgeon before (e.g., preoperatively) or during the surgical procedure (e.g., intraoperatively) to create, review, verify, update, modify and/or implement a surgical plan. In some examples, MR system 212 may also be used after the surgical procedure (e.g., postoperatively) to review the results of the surgical procedure, assess whether revisions are required, or perform other postoperative tasks. To that end, MR system 212 may include a visualization device 213 that may be worn by the surgeon and (as will be explained in further detail below) is operable to display a variety of types of information, including a 3D virtual image of the patient's diseased, damaged, or postsurgical joint and details of the surgical plan, such as a 3D virtual image of the prosthetic implant components selected for the surgical plan, 3D virtual images of entry points for positioning the prosthetic components, alignment axes and cutting planes for aligning cutting or reaming tools to shape the bone surfaces, or drilling tools to define one or more holes in the bone surfaces, in the surgical procedure to properly orient and position the prosthetic components, surgical guides and instruments and their placement on the damaged joint, and any other information that may be useful to the surgeon to implement the surgical plan.” Paragraph 0183 “Storage system 206 also can include data identifying the implant components selected for a particular patient (e.g., type, size, etc.), surgical guides selected for a particular patient, and details of the surgical procedure, such as entry points, cutting planes, drilling axes, reaming depths, etc.” Intraoperative data is captured by the MR system in addition to the operative data captured by smart implants provided as an example in the rationale of claim 1.).
Regarding claim 20, Poltaretskyi teaches the non-transitory computer readable medium of claim 19, wherein the artificial intelligence model is trained to generate the operative plan at least based on training data (Paragraph 0195 “virtual planning system 102 may use machine learning techniques to develop the preliminary surgical plan based on information in the patient's virtual case file.”); and
wherein the operative plan comprises:
a list of medical instruments for use during the surgical procedure; and/or a list of surgical steps to perform the surgical procedure (Paragraph 0162 “Use of these planning tools typically results in generation of a preoperative surgical plan, complete with an implant and surgical instruments that are selected or manufactured for the individual patient.”),
wherein each surgical step is associated with one or more of the medical instruments from the list of medical instruments (Paragraph 0221 “Examples of preoperative planning content 702 may include a surgical plan for a shoulder arthroplasty, virtual 3D model information representing scapula and/or glenoid bone, or representing humeral bone, with virtual 3D model information of instruments to be applied to the bone or implants to be positioned on or in the bone.”).
Claims 2 is rejected under 35 U.S.C. 103 as being unpatentable over Poltaretskyi (US 2019/0380792 A1) in view of Daley (US 2022/0084652 A1), and further in view of Nawana et al. (US 9,129,054 B2), hereafter Nawana.
Regarding claim 2, Poltaretskyi teaches wherein the intraoperative metrics comprise duration of surgery ([0588] “A record of the surgical procedure can be very helpful or important for safety tracking, quality control, legal compliance, analysis of the surgical procedure, tracking of how many times an instrument or other surgical item has been used, instrument age, instrument longevity, or other reasons…. By using surgical item use to track each step of the procedure and by recording the time that each surgical item is used, the system may record a very accurate picture of the entire surgical procedure.”), implant size, implant selection, implant position (The preoperative plans include implant type and position. Paragraphs 0797-0800 give examples where surgeons may deviate from the postoperative plan and use different implant types or positions. The saved plans are modified when this occurs. [0800] “In accordance with a technique of this disclosure, a computing system may obtain an information model specifying a first surgical plan, which may be a preoperatively-defined surgical plan. The computing system may modify the first surgical plan during intraoperative phase 306 of an orthopedic surgery to generate a second surgical plan (FIG. 3).” Also see the sensors and measurements in 0070 of Daley, showing that implant position, displacement, and blood flow are recorded intraoperatively and postoperatively.), postoperative pain, postoperative number of steps, or postoperative range-of-motion values ([0853] “In such examples, the postoperative health outcomes of the training data patients may include one or more of: postoperative range of motion, presence of postoperative infection, or postoperative pain.”).
However, Poltareskyi fails to teach recording blood loss during surgery. However, Nawana teaches wherein the intraoperative metrics comprise blood loss ([Col. 44, lines 42-50] “FIGS. 14-16 illustrate embodiments of various types of data that can be selectively displayed on a user interface accessible in the OR. FIG. 14 illustrates a user interface 76 showing data indicating a progress of the surgery as gathered by the system 10 including a running total case time (e.g., a continually updated time length of the surgery), a total amount of patient blood loss, and a running total amount of spinal disc removal (e.g., a continually updated amount of spinal disc removed from the patient during the surgery).”).
Poltareskyi and Nawana are analogous in the art to the claimed invention because both teach methods of surgical planning, recording metrics, and reviewing the metrics to inform future surgical plan-making and decisions. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Poltaretskyi’s invention by recording blood loss intraoperatively. This modification would help to ensure the safety of the patient ([Col. 44, lines 50-55] “The progress data can help the surgery stay on schedule, help ensure safety of the patient (e.g., by considering whether the patient's blood loss reaches an unsafe level), and help the surgery meet its goals (e.g., by considering whether a desired amount of tissue is removed from the patient)”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Macdonald et al. (US 2014/0013565 A1) teaches generating a computer recommendation for a preoperative surgical plan based on past cases. When the surgical plan is used, patient outcomes are recorded and used in a feedback loop to improve the parameters of computer recommendation algorithm to improve its recommendations for future similar patients.
Lambrechts et al. (Artificial Intelligence Based Patient-Specific Preoperative Planning Algorithm for Total Knee Arthroplasty. Frontiers in Robotics and AI, 9.) teaches utilizing artificial intelligence for generating patient-specific surgical plans for total knee arthroplasty.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC JAMES SHOEMAKER whose telephone number is (571)272-6605. The examiner can normally be reached Monday through Friday from 8am to 5pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner' s supervisor, JENNIFER MEHMOOD, can be reached at (571)272-2976. The fax phone number for the organization where this application or proceeding is assigned is (571)273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Eric Shoemaker/
Patent Examiner
/JENNIFER MEHMOOD/Supervisory Patent Examiner, Art Unit 2664