FIG. 5 illustrates a flowchart showing a technique 500 for evaluating kinematic alignment using a robotic surgical device for a surgical knee procedure in accordance with some embodiments. The technique 500 may be performed using a processor, such as a processor of a robotic surgical system to perform the following operations. In an example, a robotic controller is used to perform the following operations. The robotic controller may include the processor or the processor may include the robotic controller.

The technique 500 includes an operation 502 to control a robotic arm to move a tibia throughout a range of motion for a knee. In an example, operation 502 includes moving the robotic arm using force assist from the robotic arm. In another example, operation 502 includes sending an instruction to the robotic arm to move the tibia automatically and without surgeon interaction.

The technique 500 includes an operation 504 to obtain a series of measurements of a gap distance for the knee throughout the range of motion. Operation 504 may include using position data of the robotic arm to evaluate the gap distance for the knee throughout the range of motion. For example, the position data may be derived from a robotic coordinate system.

The technique 500 includes an operation 506 to determine, based on the 3D model and the series of measurements, a tibial resection location. Operation 506 may include determining a tibial cut plane such that after the tibia is resected and an implant is inserted, the gap distance between a femur and the tibia of the knee is minimized throughout the range of motion. Minimizing the gap distance may include minimizing an overall gap distance, a medial gap distance, a lateral gap distance, or the like. The technique 500 may be used to minimize error from an ideal rectangle or trapezoid to the gap distance across the range of motion.

In an example, operation 506 includes using the series of measurements as an input to a machine learning engine. The machine learning engine may be trained using prior gap distance measurements and outcome information (e.g., from previous range of motion tests, which may have been performed by a robotic arm or manually). The machine learning engine may output the tibial resection location. For a particular patient, prior gap distance measurements from a prior surgery on the non-operative knee (e.g., the other side, right or left) can be used to plan the mechanics and balancing of the operative knee if the outcome information indicates a favorable outcome from the prior surgery on the non-operative knee.

The technique 500 includes an operation 508 to update a 3D plan for an orthopedic procedure on the knee with the tibial resection location. In an example, operation 508 includes generating a range of motion gap distance model based on the series of measurements, including a medial gap distance and a lateral gap distance at three or more locations along the range of motion. In this example, the three or more locations may occur every degree throughout the range of motion. The operation 508 may include updating a planned implant based on the series of measurements. For example, updating the planned implant may include generating an implant shape based on a maximum medial gap distance and a maximum lateral gap distance in the series of measurements.

In an example, operation 508 may include planning a resection to result in a gap profile that most closely matches the gap profile determined by the range of motion assessment. The determination of what matches best may be done by averaging the gaps or by the error minimization process. In an example, a trapezoidal implant may be used to leave a slightly greater gap on one side (e.g., medial or lateral) purposefully.

The technique 500 may include preoperatively generating a 3D plan for an orthopedic procedure on the knee before controlling the robotic arm to move the tibia throughout the range of motion. The technique 500 may include an operation to remove osteophytes from the tibia of the knee before controlling the robotic arm to move the tibia throughout the range of motion. The technique 500 may include generating information indicative of an axis through a femur of the knee.

FIG. 6 illustrates a robotic surgical system 600 for performing techniques described herein, in accordance with some embodiments. The robotic surgical system 600 includes a robotic surgical arm 602 including a sensor 604. The sensor 604 may include an accelerometer, gyroscope, or other sensor, any of which may be used to determine a location of a portion of the robotic surgical arm 602. The sensor may output measurements, such as a series of measurements throughout a range of motion of a knee as the robotic surgical arm 602 moves a tibia of the knee.

The robotic surgical arm 602 may include a motor, such as for autonomous movement or for use in as a force assist. The motor may be used to conduct the range of motion test.

A control system 618 (e.g., a robotic controller), may include a processor 620 and memory 622. The control system 618 may be a part of the robotic surgical arm 602 or may be communicatively coupled to the robotic surgical arm 602. The processor 602 may be used to perform the technique 500 or operations thereof.

A display device 614 may be a part of the robotic surgical arm 602 or may be communicatively coupled to the robotic surgical arm 602. The display device 614 may be used to display a user interface 616.

In an example, the display device 1614 may be used to display results (e.g., measurements, a tibial resection location, a cut plane, a recommended trial or implant, etc.) of a range of motion test on the user interface 616. The results may include gap distance information, such as at different angles during a range of motion test. The gap distance information may be derived from a sensor, such as a sensor 604, which may be on the robotic surgical arm 602.

FIG. 7 illustrates a machine learning engine for evaluating range of motion data to aid in knee arthroplasty and other surgical procedures in accordance with some embodiments. A system may calculate one or more weightings for criteria based upon one or more machine learning algorithms. FIG. 7 shows an example machine learning engine 700 according to some examples of the present disclosure. Machine learning engine 700 may be part of the system 600 of FIG. 6, for example implemented using a database, a server, etc., or the like.

Machine learning engine 700 utilizes a training engine 702 and a prediction engine 704. Training engine 702 inputs historical transaction information 706 for historical actions of stored or generated at a robotic surgical device, for example, into feature determination engine 708. The historical action information 706 may be labeled with an indication, such as a degree of success of an outcome of a surgical procedure, which may include pain information, patient feedback, implant success, ambulatory information, or the like. In some examples, an outcome may be subjectively assigned to historical data, but in other examples, one or more labelling criteria may be utilized that may focus on objective outcome metrics (e.g., pain rating, survey score, a patient satisfaction score, such as a forgotten knee score, a Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) score, or the like).

Feature determination engine 708 determines one or more features 710 from this historical information 706. Stated generally, features 710 are a set of the information input and is information determined to be predictive of a particular outcome. Example features are given above. In some examples, the features 710 may be all the historical activity data, but in other examples, the features 710 may be a subset of the historical activity data. The machine learning algorithm 712 produces a model 720 based upon the features 710 and the labels. The historical action information 706 may include a gap distance within the knee of the patient, a varus/valgus angle, other aspects of soft tissue or alignment of the knee, an axis through the distal femur, a position of a femoral component, a tibial cut location, a shape of an implant, or the like. The historical action information 706 may include measurements taken, for example, at degree, half degree, or quarter degree increments along a range of motion.

In the prediction engine 704, current action information 714 (e.g., a surgical plan, an action to be taken or a last action taken, such as by a robotic surgical device, or the like) may be input to the feature determination engine 716. Feature determination engine 716 may determine the same set of features or a different set of features from the current information 714 as feature determination engine 708 determined from historical information 706. In some examples, feature determination engine 716 and 708 are the same engine. Feature determination engine 716 produces feature vector 718, which is input into the model 720 to generate one or more criteria weightings 722. The training engine 702 may operate in an offline manner to train the model 720. The prediction engine 704, however, may be designed to operate in an online manner. In an example, the model 720 may be periodically updated via additional training or user feedback (e.g., an update to a technique or procedure).

The machine learning algorithm 712 may be selected from among many different potential supervised or unsupervised machine learning algorithms. Examples of supervised learning algorithms include artificial neural networks, Bayesian networks, instance-based learning, support vector machines, decision trees (e.g., Iterative Dichotomiser 3, C4.5, Classification and Regression Tree (CART), Chi-squared Automatic Interaction Detector (CHAID), and the like), random forests, linear classifiers, quadratic classifiers, k-nearest neighbor, linear regression, logistic regression, and hidden Markov models. Examples of unsupervised learning algorithms include expectation-maximization algorithms, vector quantization, and information bottleneck method. Unsupervised models may not have a training engine 702. In an example embodiment, a regression model is used and the model 720 is a vector of coefficients corresponding to a learned importance for each of the features in the vector of features 710, 718.

FIG. 8 illustrates a block diagram of an example machine 800 upon which any one or more of the techniques discussed herein may perform in accordance with some embodiments. In alternative embodiments, the machine 800 may operate as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, the machine 800 may operate in the capacity of a server machine, a client machine, or both in server-client network environments. In an example, the machine 800 may act as a peer machine in peer-to-peer (P2P) (or other distributed) network environment. The machine 800 may be a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile telephone, a web appliance, a network router, switch or bridge, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations.

Machine (e.g., computer system) 800 may include a hardware processor 802 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 804 and a static memory 806, some or all of which may communicate with each other via an interlink (e.g., bus) 808. The machine 800 may further include a display unit 810, an alphanumeric input device 812 (e.g., a keyboard), and a user interface (UI) navigation device 814 (e.g., a mouse). In an example, the display unit 810, input device 812 and UI navigation device 814 may be a touch screen display. The machine 800 may additionally include a storage device (e.g., drive unit) 816, a signal generation device 818 (e.g., a speaker), a network interface device 820, and one or more sensors 821, such as a global positioning system (GPS) sensor, compass, accelerometer, or other sensor. The machine 800 may include an output controller 828, such as a serial (e.g., Universal Serial Bus (USB), parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connection to communicate or control one or more peripheral devices (e.g., a printer, card reader, etc.).

The storage device 816 may include a machine readable medium 822 on which is stored one or more sets of data structures or instructions 824 (e.g., software) embodying or utilized by any one or more of the techniques or functions described herein. The instructions 824 may also reside, completely or at least partially, within the main memory 804, within static memory 806, or within the hardware processor 802 during execution thereof by the machine 800. In an example, one or any combination of the hardware processor 802, the main memory 804, the static memory 806, or the storage device 816 may constitute machine readable media.

While the machine readable medium 822 is illustrated as a single medium, the term “machine readable medium” may include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) configured to store the one or more instructions 824. The term “machine readable medium” may include any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 800 and that cause the machine 800 to perform any one or more of the techniques of the present disclosure, or that is capable of storing, encoding or carrying data structures used by or associated with such instructions. Non-limiting machine readable medium examples may include solid-state memories, and optical and magnetic media.

The instructions 824 may further be transmitted or received over a communications network 826 using a transmission medium via the network interface device 820 utilizing any one of a number of transfer protocols (e.g., frame relay, internet protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks may include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), mobile telephone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks (e.g., Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards known as Wi-Fi®, IEEE 802.16 family of standards known as WiMax®), IEEE 802.15.4 family of standards, peer-to-peer (P2P) networks, among others. In an example, the network interface device