Algorithm-based optimization for knee arthroplasty procedures

Inventors

McKinnon, Brian W. • Marinescu Tanasoca, Ruxandra Cristiana • Winebarger, Randy C. • Bowers, JR., William L. • Wiebe, III, James Bennett • Lenz, Nathaniel Milton • Wilkinson, Zachary Christopher • Haddock, Sean M. • LANDON, Ryan Lloyd • Nikou, Constantinos • Jaramaz, Branislav • Torrie, Paul Alexander

Assignees

Smith and Nephew Orthopaedics AG • Smith and Nephew Asia Pacific Pte Ltd • Smith and Nephew Inc

Abstract

A method for optimizing a knee arthroplasty surgical procedure includes receiving pre-operative data comprising (i) anatomical measurements of the patient, (ii) soft tissue measurements of the patient's anatomy, and (iii) implant parameters identifying an implant to be used in the knee arthroplasty surgical procedure. An equation set is selected from a plurality of pre-generated equation sets based on the pre-operative data. During the knee arthroplasty surgical procedure, patient-specific kinetic and kinematic response values are generated and displayed using an optimization process. The optimization process includes collecting intraoperative data from one or more surgical tools of a computer-assisted surgical system, and using the intraoperative data and the pre-operative data to solve the equation set, thereby yielding the patient-specific kinetic and kinematic response values. A visualization is then provided of the patient-specific kinetic and kinematic response values on the displays.

Core Innovation

The invention provides methods, systems, and apparatuses for algorithm-based optimization of arthroplasty surgical procedures. A method is described wherein pre-operative data, including anatomical measurements, soft tissue measurements, and implant parameters for a patient, is received. Based on this data, an appropriate equation set is selected from multiple pre-generated equation sets. During surgery, intraoperative data is collected using surgical tools connected to a computer-assisted surgical system, and an optimization process solves the equation set using pre-operative and intraoperative data to generate patient-specific kinetic and kinematic response values. These response values are then made available to the surgical team, often in a visual and interactive format.

The problem addressed by the invention is the need to improve the planning and real-time adaptation of surgical workflows in procedures such as knee arthroplasty. Traditional approaches rely heavily on preoperative plans or require extensive intraoperative modifications by the surgeon, often lacking a robust mechanism for integrating diverse data sources and optimizing outcomes dynamically based on patient-specific factors and evolving data during surgery.

To overcome these issues, the invention introduces an approach that can include either an equation set-based solution or a machine learning model trained on databases of past surgical data. The optimization process can compare generated patient-specific response values with surgeon-specified goals, applying weights to different outcomes and providing visualizations—such as slider scales or interactive displays—showing differences between actual and target values. Machine learning models, such as neural networks or support vector machines, can be used to predict kinetic and kinematic responses, and can dynamically update predictions if pre-operative information changes intraoperatively.

Claims Coverage

The patent features three independent claim inventions focusing on equation set optimization, machine learning optimization, and a system for interactive surgical optimization.

The inventive features are the real-time optimization of surgical plans through equation set solutions and machine learning models, as well as a computer-assisted system that integrates these processes with interactive visualization and intraoperative data.

Stated Advantages

Documented Applications