# US 2023/0267249 A1 · Using numerical methods to optimize implant design

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0267249 A1
- Document ID: US20230267249A1
- Status: Published application
- Kind: A1
- Application number: 18/108,885
- Filed: 2023-02-13
- Published: 2023-08-24
- Earliest claimed: 2022-02-21
- Assignees: Zimmer, Inc.
- Applicants: Zimmer, Inc.
- Inventors: Philippe Favre; Yang Wook Son; Christine Mirja Mueri
- Web page: https://patentgrep.com/patent/US20230267249A1

## CPC

- A61F 2/30942: {for designing or making customized prostheses, e.g. using templates, CT or NMR scans, finite-element analysis or CAD-CAM techniques}
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06F 30/23: using finite element methods [FEM] or finite difference methods [FDM]
- A61B 2034/108: {Computer aided selection or customisation of medical implants or cutting guides}
- A61F 2002/30948: {using computerized tomography, i.e. CT scans}
- A61F 2002/30952: {using CAD-CAM techniques or NC-techniques}
- A61F 2002/30985: {using three dimensional printing [3DP]}
- A61F: FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS (dental prosthetics A61C)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

Disclosed herein are systems and methods for manufacturing a prosthetic. The systems and methods can include receiving patient data and determining optimal design parameters for the prosthetic using the patient specific data and a machine learning model. The optimal design parameters can be exported so that the prosthetic can be manufactured.

## Claims

### Claim 1

A method for manufacturing a prosthetic, the method comprising:
receiving, at a computing device, patient specific data;
determining, by the computing device, optimal design parameters for the prosthetic using the patient specific data and a model; and
exporting, by the computing device, the optimal design parameters.

### Claim 2 (depends on 1)

The method of claim 1, where determining the optimal design parameters includes determining a size of a placement fixture.

### Claim 3 (depends on 1)

The method of claim 1, where determining the optimal design parameters includes determining a number of placement fixtures.

### Claim 4 (depends on 1)

The method of claim 1, where determining the optimal design parameters includes determining a shape of a placement fixture.

### Claim 5 (depends on 1)

The method of claim 1, where determining the optimal design parameters includes determining a location of a placement fixture.

### Claim 6 (depends on 1)

The method of claim 1, where determining the optimal design parameters includes iterating over a plurality of guesses for the optimal design parameters.

### Claim 7 (depends on 1)

The method of claim 1, further comprising generating a plurality of designs for the prosthetic, each of the plurality of designs including a different permutation of design parameters.

### Claim 8 (depends on 1)

The method of claim 1, wherein
receiving the patient specific data comprises receiving a scan of a patient’s anatomy; and
the method further comprises extracting design constraints for the prosthetic from the scan.

### Claim 9 (depends on 1)

The method of claim 1, wherein exporting the optimal design parameters includes transmitting the optimal design parameters to an automated manufacturing device.

### Claim 10

A system for manufacturing a prosthetic, the system comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform actions comprising:
receiving patient specific data,
determining optimal design parameters for the prosthetic using the patient specific data and a machine learning model, and
exporting the optimal design parameters.

### Claim 11 (depends on 10)

The system of claim 10, where determining the optimal design parameters includes determining a size of a placement fixture.

### Claim 12 (depends on 10)

The system of claim 10, where determining the optimal design parameters includes determining a number of placement fixtures.

### Claim 13 (depends on 10)

The system of claim 10, where determining the optimal design parameters includes determining a size and shape of a placement fixture.

### Claim 14 (depends on 10)

The system of claim 10, wherein the actions further comprise generating a plurality of designs for the prosthetic, each of the plurality of designs including a different permutation of design parameters.

### Claim 15 (depends on 10)

The system of claim 10, wherein
receiving the patient specific data comprises receiving a scan of a patient’s anatomy; and
the actions further comprise extracting design constraints for the prosthetic from the scan.

### Claim 16

A method for generating a machine learning model used to design a prosthetic, the method comprising:
receiving, by a computing device, a plurality of input parameters, each of the plurality of input parameters corresponding to a parameter of at least one of a plurality of prosthetic designs;
generating, by the computing device, an initial guess for the machine learning model based on the plurality of input parameters;
optimizing, by the computing device, parameters of the machine learning model using the initial guess for the machine learning model and the plurality of input parameters; and
exporting, by the computing device, the machine learning model having optimized parameters.

### Claim 17 (depends on 16)

The method of claim 16, wherein optimizing the parameters of the machine learning model comprises training the machine learning model using a set of finite element analyses performed on models of the prosthetic and at least a subset of the input parameters.

### Claim 18 (depends on 16)

The method of claim 16, wherein the plurality of input parameters comprises patient data for a plurality of patients.

### Claim 19 (depends on 16)

The method of claim 16, further comprising dividing the plurality of input data into a training subset used in optimizing the parameters of the machine learning model and a validation subset used for confirming a validity of the machine learning model.

### Claim 20 (depends on 16)

The method of claim 16, wherein receiving the plurality of input parameters comprises:
receiving a scan of a patient’s anatomy for a plurality of patients; and
extracting at least one of the input parameters from the scan of the patient’s anatomy for each of the plurality of patients.
